Borrowing it
Nothing to install: this file belongs to vmihalis/hacker-bob. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vmihalis/hacker-bob/main/.claude/skills/bob-evaluate-runner/SKILL.mdgit clone --depth 1 https://github.com/vmihalis/hacker-bobWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vmihalis/hacker-bob/bob-evaluate-runner)<a href="https://agentmods.dev/skills/vmihalis/hacker-bob/bob-evaluate-runner"><img src="https://agentmods.dev/badge/skills/vmihalis/hacker-bob/bob-evaluate-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vmihalis/hacker-bob/bob-evaluate-runner"><img src="https://agentmods.dev/badge/skills/vmihalis/hacker-bob/bob-evaluate-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 190 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 276 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 412 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Rogue Agent · line 449 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 449 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.23772 |
| Opus 5.5 | $0.00010 | $0.09509 |
| Sonnet 5.5 | $0.00005 | $0.04754 |
| Haiku 4.5 | $0.00003 | $0.02377 |
Grade A, and why
bob-evaluate-runner scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Dispatch `browser_behavior_probe` (the browser-shaped sibling of HTTP `behavior_probe`) when the surface is best exercised through the Patchright session driver: web SPA targets with heavy client-side JS or routing, WebA How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the ORCHESTRATOR for Bob, an autonomous security evaluation system. Coordinate agents, auth capture, verification, grading, and reporting. Do not evaluate yourself. Input: $ARGUMENTS (target URL, local repo path, a contract token (CAIP-10 namespace:reference:address or ergonomic family:chainId:address), or resume [domain] [force-merge], optionally --no-auth, --private-targets, one of --normal|--paranoid|--yolo, --deep, --egress <profile>, --block-internal-hosts, --allow-internal-hosts, --rpc family:chainId=url, and the repo-mode flags --build, --allow-network, --target-id <id>)
Target-axis branching (web, OSS repo, contract)
The non-flag tokens of $ARGUMENTS are a multi-axis target set; the first non-flag token's axis at the highest precedence (web > repo > contract, O-P6) selects the PRIMARY axis and the remaining tokens attach as companions:
- It is a URL when it starts with
http://orhttps://. Web mode is in force; derivetarget_domainfrom the parsed URL hostname exactly (ASCII-normalized and without scheme or port), callbob_init_session({ target_domain, target_url, ... })in SETUP, and dispatch HTTP-shaped lenses (seed_mapping,surface_scout,behavior_probe,browser_behavior_probe,control_check,claim_development,impact_correlation,reproduction_check,evidence_capture,coverage_closeout). For an explicitly operator-attested--private-targetsURL, preserve the loopback/RFC1918 IPv4 hostname byte-for-byte (for examplehttp://127.0.0.1:8081/...usestarget_domain: "127.0.0.1"); never invent alocalhost-*slug or include the port. Repo and contract modes own their separate slug derivations below. - It is a local repo path when it does not start with
http:///https://, starts with/,~, or./, and resolves to a local directory. OSS repo mode is in force; callbob_init_repo_session({ repo_path, ... })in SETUP and dispatch the OSS lenses (code_surface_scout,taint_trace,fuzz_run) per O-D5 / O.6. - It is a contract when it is a CAIP-10
namespace:reference:address(e.g.eip155:1:0x...) or the ergonomicfamily:chainId:addressform (familyin the chain families). A PURE chain:addr target (no url/repo present) is contract mode: callbob_init_contract_session({ contracts: [...] })in SETUP. A MIXED target attaches contracts as companions to the primary: web primary →bob_init_session({ target_url, contracts: [...] }), repo primary →bob_init_repo_session({ repo_path, contracts: [...] }). Both axes bind (chain authority + onesmart_contractsurface per contract, unioned into the frontier) while the web/repo and chain scope gates stay INDEPENDENT (O-P6) — a companion never widens HTTP/PSL scope or grants cross-axis authority. The--rpc family:chainId=urlflag binds a chain's RPC endpoint and is public-HTTPS-only. - Refuse remote paths (anything that looks like
git@host:owner/repo.git,git+https://...,ssh://..., ahost:prefix, or a bare GitHubowner/reposlug). Per O-P1, this entry point never performs agit clone. Tell the operator to check out the repo locally and re-invoke/bob-evaluate <local-path>. Per O-P2, source visibility is not permission to attack the hosted instance. Repo mode does NOT authorize HTTP probing of any deployed sibling of the codebase. If the operator wants to mix repo evaluation with live HTTP work, they MUST pass an explicit second target URL (cross-mode session per O-P6); never infer atarget_urlfrom apackage.json, README, or repo metadata.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 457 lines · 25 tokens per session scan A b76e0722cf78
bob-evaluate-runner is a skill published in the GitHub repository vmihalis/hacker-bob (100 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 23,772 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fix-plan
Generate an EPSS/KEV-prioritised remediation plan from a scan. Returns the top findings ranked by real-world exploitation risk with copy-paste upgrade commands, semver-jump risk classification (PATCH/MINOR/MAJOR), and a recommendation per package. Use when the user asks for "what should I fix first", "remediation…
scan-full
Comprehensive scan covering project dependencies PLUS OS/system packages (Homebrew on macOS, apt/dnf on Linux) PLUS installed IDE extensions (VS Code marketplace + JetBrains plugins). Most other supply-chain scanners only check project manifests and miss system + IDE surfaces. Use whenever the user asks for "complete…
scan
Full project dependency scan with live advisory fetch (OSV, NVD, GHSA) and EPSS exploit-probability + CISA KEV prioritisation. Covers npm and PyPI manifests + lockfiles. Use when the user wants thorough, up-to-date supply-chain CVE coverage for their project — but does NOT need system packages or IDE extensions (for…
supply-chain-scan
Scan a workspace for supply-chain CVEs across project dependencies, system packages (Homebrew/apt), and IDE extensions (VS Code, JetBrains). Findings ranked by EPSS exploit probability and CISA KEV presence — not just CVSS severity. Use when the user asks about supply-chain risk, dependency vulnerabilities, or wants…
why
Explain why a specific vulnerable package is in the project — direct vs transitive dependency, which CVE IDs apply, EPSS exploit-probability score, whether it's on the CISA KEV catalog, and the recommended fix command. Use when the user asks "why is X vulnerable", "where does X come from", or "is X actually…
quick-scan
Fast cached-only scan of project dependencies for high-severity CVEs. Uses the local advisory cache without making fresh network calls — sub-second for most projects. Use when the user wants a pre-commit check, a fast pulse on supply-chain risk, or is offline. For thorough live-advisory checks use scan or…