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

to-spec

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes conversation context and codebase content to generate a specification document, which is then published to an external issue tracker. This creates an attack surface where malicious instructions in the ingested data could influence the agent's behavior.
  • Ingestion points: The skill instructions direct the agent to explore the repository and use the current conversation context (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the process.
  • Capability inventory: The agent has capabilities to read the codebase and write to a project issue tracker (SKILL.md).
  • Sanitization: There are no explicit instructions for filtering or sanitizing the input data before it is synthesized and published.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:03 AM
Security Audit — agent-trust-hub — to-spec