skills/gannonh/skills/readme/Gen Agent Trust Hub

readme

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides guidelines for writing factual documentation and contains no evidence of malicious behavior, obfuscation, or unauthorized data access.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes project files to gather context, which is an inherent part of its functionality. This introduces a surface for indirect prompt injection if project files contain malicious instructions.
  • Ingestion points: The skill reads README.md, manifest files (package.json, pyproject.toml, go.mod, Cargo.toml), LICENSE, and top-level source directories.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present.
  • Capability inventory: The skill is limited to text generation and suggesting commands for the user to run.
  • Sanitization: No sanitization or filtering of the ingested content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:48 PM
Security Audit — agent-trust-hub — readme