to-spec

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository and conversation context to generate output for an external issue tracker, creating an attack surface where malicious content in the codebase could influence the agent's actions.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to explore the repository and use current conversation context as input for synthesis.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to delimit untrusted codebase content from the agent's instructions.
  • Capability inventory: The agent performs repository exploration (read capability) and publishes synthesized specifications to a project issue tracker (write capability).
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content ingested from the codebase before it is published.
  • [NO_CODE]: The skill does not include any executable scripts, binaries, or configuration-level command execution, relying solely on natural language instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 09:28 AM