to-tickets

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, including project documentation (CLAUDE.md, AGENTS.md), issue trackers, and arbitrary URLs, which could contain adversarial instructions. 1. Ingestion points: Fetches content from external URLs and issue trackers; reads CLAUDE.md and AGENTS.md (SKILL.md). 2. Boundary markers: Absent; the instructions do not define specific delimiters or warnings to ignore instructions embedded within the fetched content. 3. Capability inventory: The skill possesses the capability to write files to the local .scratch directory and create issues on external trackers. 4. Sanitization: There is no mention of sanitizing or validating the input data before it is used to generate tickets.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch specifications, issues, or content from supplied URLs. While no specific domains are hardcoded, fetching arbitrary external content is a recognized risk vector.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:00 AM
Security Audit — agent-trust-hub — to-tickets