security

A security guide for reviewing the parts of a coding system that install packages, run commands, handle dependencies, publish releases, or connect related components. It also records evidence from security checks.

In plain words
What is it for?
Use it when reviewing installers, shell execution, dependencies, publication, release gates, vulnerability results, signatures, and security evidence.
Why use it?
It helps reviewers identify unsafe release and execution paths and distinguish internal consistency checks from proof against a fully compromised workspace.

Agent

Install

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.

agentmods
npx agentmods add agents/hannsxpeter/godpowers/security
Clone the repo
git clone --depth 1 https://github.com/hannsxpeter/godpowers
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,264 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01264
Opus 5 $0.00000 $0.00632
Sonnet 5 $0.00000 $0.00253
Haiku 4.5 $0.00000 $0.00126

Measured yesterday against content hash a5bf64244efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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 yesterday.

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.

agents/security.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

  • [DECISION] This pillar captures security boundaries for Godpowers runtime and release work.

Context

  • [DECISION] Installer, bridge, shell-execution, dependency, and publication surfaces receive adversarial review before release.

Decisions

  • [DECISION] lib/evidence.resolveReviewEvidence is a read-only local resolver that checks one exact record against expected claim, command, canonical substep, freshness, digest-bound gate event, and event hash chain.
  • [DECISION] Stage 2 receives the resolver's sanitized projection without raw ledger records, event attributes, commands, claims, stdout tails, or stderr tails.
  • [DECISION] The resolver proves internal consistency only inside a trusted workspace; it does not authenticate against an actor able to rewrite every trusted file and recompute the chain.
  • [DECISION] The 6.2.0 prepublication gate passed at 2026-08-19T10:07:48.020Z against hardening revision sha256:5f65a4de4bb0ab7dcce5e7fb11c182a77345f23b2e6f75077c549ccef4ce9268 with zero Critical findings.
  • [DECISION] The isolated exact 6.2.0 package pair reported zero vulnerabilities, and npm audit signatures verified registry signatures and attestations for all 5 installed packages.
  • [DECISION] The 6.3.0 decision writer and reader share one bounded allowlisted validator that rejects credential fields, common provider tokens, URL userinfo, all query strings, and unsafe fragments before append or projection.
  • [DECISION] The 6.3.0 route loader derives command authority from canonical filenames and rejects duplicate, spoofed, or noncanonical route YAML.
  • [DECISION] Unknown route prerequisite predicates fail closed, and every named non-prefixed predicate used by a canonical route has explicit bounded behavior.
  • [DECISION] Event readers reject traversal and linked run paths, and event snapshots fail closed above 8 MiB or 50,000 lines.
  • [DECISION] SkillUI validates remote targets but never passes URLs or remote repository locations to the external CLI; remote forms require an already reviewed local directory.
  • [DECISION] Runtime verification profiles and debug feedback records cap collections and recursive validation before generating result objects.
  • [DECISION] Manual pack workflow inputs cross through environment variables, then pass a pack allowlist and strict SemVer validation before shell use.
  • [DECISION] Root and MCP recovery publication requires registry integrity and shasum to match the exact packed candidates before promotion.
  • [DECISION] The final 6.3.0 harden gate passed with one executed-backed release command, and the fresh prepublication gate passed against hardening revision sha256:69bd088dc44e405b144536bd51701088bb0da7d5e2200685e9b3e13be7403f5f with zero unresolved or accepted Critical findings.
  • [DECISION] The optional operations-pack setup template keeps secrets off command arguments, rejects tracked environment destinations, verifies exact repository authority, and uses temporary replacement with cleanup and error propagation.
  • [DECISION] The exact published 6.3.0 root, MCP, and operations-pack install reported zero vulnerabilities, and npm audit signatures verified registry signatures and attestations for all 6 installed packages.

Read the full file on GitHub · 79 lines

Changes

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.

  1. yesterday First seen · 79 lines · 0 tokens per session scan A a5bf64244efe

Subscribe to this mod's changes

security is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,264 tokens. 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.