to-issues

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns such as persistence, credential theft, or unauthorized data exfiltration were detected. The skill's behavior is consistent with its stated purpose of decomposition and issue management.
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it ingests untrusted data from external sources.
  • Ingestion points: SKILL.md (Step 1) specifies fetching issue bodies and comments from a tracker which are controlled by external users.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the fetched issue content.
  • Capability inventory: The agent can read the local codebase (Step 2) and create new issues on the tracker (Step 5).
  • Sanitization: No explicit sanitization or filtering of the fetched data is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill includes references to an official repository on GitHub for credits and attribution. This involves a well-known service and does not trigger execution of untrusted remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 07:25 AM
Security Audit — agent-trust-hub — to-issues