Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kings0527/agent-skills --skill analyze-authorized-local-targetsgit clone --depth 1 https://github.com/kings0527/agent-skillsWrote 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/kings0527/agent-skills/analyze-authorized-local-targets)<a href="https://agentmods.dev/skills/kings0527/agent-skills/analyze-authorized-local-targets"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/analyze-authorized-local-targets/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/kings0527/agent-skills/analyze-authorized-local-targets"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/analyze-authorized-local-targets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00114 | $0.01069 |
| Opus 5 | $0.00057 | $0.00535 |
| Sonnet 5 | $0.00023 | $0.00214 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
analyze-authorized-local-targets scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Authorized Local Targets
Treat authorization as a scoped user attestation, not a blanket assumption. This skill narrows tool behavior; it does not disable platform safeguards or prove ownership by itself.
Establish scope before tool use
Require the following facts before invoking IDA MCP, Frida, a debugger, or a shell command that interacts with the target:
- Authorization basis: user-owned asset or explicit authorization.
- Exact target: local path plus SHA-256 when available, or mobile bundle ID plus a user-chosen device alias.
- Environment: local computer or a directly connected user-owned device.
- Allowed actions: choose only the actions needed for the current task.
- Network boundary: disabled by default; external targets are out of scope.
Do not infer ownership merely because a database is open in IDA, a process is local, a phone is jailbroken, or an MCP server exposes it. If any required fact is missing, ask one concise scope question and do not touch the target yet.
Prefer a project-local re-scope.json copied from assets/re-scope.template.json. Validate it with:
python3 scripts/validate_scope.py /absolute/path/to/re-scope.json --check-files
When the target is already loaded and its path cannot be obtained safely, require the user to confirm its path or identifier before proceeding. Never invent a hash, bundle ID, device alias, or authorization statement.
Preflight
Before acting, state a compact preflight summary:
Scope: <target identifier>
Authorization: <owned or explicit authorization>
Environment: <local host or directly connected owned device>
Allowed actions: <list>
Network: disabled
Proceed only when the current tool target matches the declared target. Stop if IDA, Frida, or another tool reports a different path, bundle ID, process, or device.
Apply tool constraints
IDA MCP and static analysis
- Start with read-only inspection: metadata, segments, imports, strings, cross-references, functions, control flow, data flow, types, and decompiler output.
- Allow renaming and comments as analysis annotations.
- Patch bytes, rewrite files, or export modified binaries only when
test-only-patchingorpatch-validationis explicitly allowed. - Keep every conclusion traceable to addresses, symbols, cross-references, or observed data.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 93 lines · 114 tokens per session scan A 31d6a484a5ef
analyze-authorized-local-targets is a skill published in the GitHub repository kings0527/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 1,069 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.