audit-docs

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as grep, git log, and gh pr list to verify the state of the repository and integrated forge data.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from external sources.
  • Ingestion points: The skill reads and processes content from pull request bodies, issue descriptions, and various documentation files in the repository.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the audited issues or PR descriptions.
  • Capability inventory: The agent has access to shell execution (grep, git, gh) and file system write capabilities when the --fix flag is used.
  • Sanitization: The skill does not define any sanitization, filtering, or validation steps for the data ingested from external sources before it is analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 12:33 AM
Security Audit — agent-trust-hub — audit-docs