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 project-specific files such as ADRs, codebase content, and context files which could theoretically contain instructions intended to influence the agent's behavior during synthesis.
  • Ingestion points: The skill reads from .agents/projects/<project>/CONTEXT.md, LINKS.md, ADRs, and the general codebase.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these project files.
  • Capability inventory: The skill performs file writes to the local repository and network-based publication to Jira or GitHub.
  • Sanitization: No specific sanitization or filtering logic is described for the content ingested from the codebase or project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:37 AM
Security Audit — agent-trust-hub — to-spec