skills/manojbajaj95/skills/wiki/Gen Agent Trust Hub

wiki

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The CI installation reference (references/install.md) includes instructions to download the skill from the author's repository using npx skills add manojbajaj95/skills. This is a documented distribution method for the tool.
  • [COMMAND_EXECUTION]: The skill uses shell commands for git operations (diff, status, rev-parse, commit, push) and interacting with the GitHub CLI (gh pr) to manage documentation changes through automated pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and summarizes repository source code during its survey and update phases. It implements security boundaries by strictly adhering to .wikiignore and .gitignore patterns to prevent the ingestion of sensitive or untrusted files. Ingestion point: Repository source files. Capability: File system write access and pull request creation. Sanitization: Enforcement of exclusion rules and explicit instructions to ignore secret values.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:00 AM
Security Audit — agent-trust-hub — wiki