skills/gastownhall/beads/beads-docs/Gen Agent Trust Hub

beads-docs

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various local scripts and tools for documentation validation, including go test ./test/docsync, ./scripts/generate-cli-docs.sh, make docs-dev, and ./mint.sh. These commands are standard for the project's development workflow and are executed within the local repository context.
  • [DATA_EXPOSURE]: Technical documentation guidelines reference internal project paths such as .beads/embeddeddolt/ and .beads/issues.jsonl. These references are used to maintain accuracy in user-facing documentation and do not involve the exposure of sensitive credentials or system-level configuration files.
  • [PROMPT_INJECTION]: The skill involves processing project-specific documentation and source code, creating an inherent surface for indirect prompt injection. 1. Ingestion points: The agent is instructed to read files in docs/, engdocs/, README.md, AGENTS.md, and *.go. 2. Boundary markers: No explicit instructions are provided to use delimiters or ignore embedded instructions within these files. 3. Capability inventory: The skill provides the ability to execute local scripts and development tools for verification and document generation. 4. Sanitization: No content sanitization or validation steps are defined for the data ingested from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:08 PM
Security Audit — agent-trust-hub — beads-docs