skills/a-canary/arc-skills/to-issues/Gen Agent Trust Hub

to-issues

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external issue trackers (issue bodies, comments) and conversation context to generate new project issues. This creates a surface where embedded instructions in those sources could attempt to influence the agent's output.
  • Ingestion points: SKILL.md (Step 1: Gather context) fetches full body and comments from issue tracker URLs or references.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the fetched issue data.
  • Capability inventory: The skill has the capability to read from the issue tracker and publish new issues.
  • Sanitization: Absent; content is processed directly into the drafting phase.
  • Mitigation: The skill includes a mandatory human-in-the-loop step (Step 4: Quiz the user) where the user must review and approve the proposed breakdown before any issues are published, which mitigates the risk of unauthorized or malicious issue creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 01:39 AM
Security Audit — agent-trust-hub — to-issues