to-goal

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions designed to influence the agent's behavior during the subsequent implementation phase.
  • Ingestion points: The skill reads content from external ticket URLs, tracker comments, and local paths under the .scratch/ directory.
  • Boundary markers: There are no instructions to use delimiters or 'ignore embedded instructions' warnings when interpolating this external data into the generated goal block.
  • Capability inventory: Although this specific skill is limited to read-only actions, the generated 'goal block' is intended for immediate use by a fresh agent session with implementation capabilities (such as file modifications and command execution).
  • Sanitization: The instructions do not specify any validation, filtering, or escaping of the ingested data before it is included in the output goal.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:14 AM
Security Audit — agent-trust-hub — to-goal