Skills
Navigate
skills/steipete/agent-scripts/clawsweeper-status/Gen Agent Trust Hub

clawsweeper-status

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The bash script scripts/clawsweeper-status.sh makes a network request to https://clawsweeper.openclaw.ai/api/exact-review-queue (or a URL defined by the CLAWSWEEPER_EXACT_REVIEW_QUEUE_URL environment variable) to fetch queue status information.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub, including issue comments, pull request titles, and workflow run names, which are then reported to the user.\n
  • Ingestion points: Data is fetched via gh api and gh pr list within the scripts/clawsweeper-status.sh script.\n
  • Boundary markers: The skill instructions in SKILL.md do not specify delimiters or instructions for the agent to ignore embedded commands within the fetched GitHub content.\n
  • Capability inventory: The skill uses the gh CLI for repository interaction and curl for network requests.\n
  • Sanitization: The script uses jq to clean and truncate lines for display purposes, but it does not perform security-specific sanitization to prevent prompt injection from the processed GitHub content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:27 PM
Security Audit — agent-trust-hub — clawsweeper-status