to-spec

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user conversation data and codebase content to generate specifications, creating a potential surface for instructions within the data to affect the agent's synthesis.
  • Ingestion points: Conversation history and repository state are accessed as described in SKILL.md.
  • Boundary markers: The skill does not implement specific delimiters or warnings to ignore instructions contained within the synthesized source data.
  • Capability inventory: The skill instructions direct the agent to publish output to an external project issue tracker.
  • Sanitization: There is no explicit sanitization or validation logic defined for the external data before it is processed or published.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform repository exploration and issue tracker interaction. These operations are essential to the skill's primary function of documenting project requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 07:48 AM
Security Audit — agent-trust-hub — to-spec