Skills
Navigate
skills/a5c-ai/babysitter/babysit-babysitter-issues/Gen Agent Trust Hub

babysit-babysitter-issues

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates an attack surface for indirect prompt injection by fetching and processing external content (GitHub issues) without user oversight.
  • Ingestion points: Fetches issue titles and URLs from the a5c-ai/babysitter repository using the gh CLI (Step 1).
  • Boundary markers: Absent; there are no delimiters or specific instructions provided to the agent to treat issue content as untrusted data.
  • Capability inventory: The skill orchestrates work via /babysitter:yolo, which includes creating branches, pushing commits, and opening pull requests.
  • Sanitization: Absent; the skill instructs the agent to process all assigned issues sequentially without user interaction or breakpoints.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI to interact with remote repositories.
  • Evidence: Executes gh issue list --repo a5c-ai/babysitter --assignee a5c-agent --state open --json number,title,url,labels --limit 50 in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 01:53 AM