skills/utarn/engineer-skills/to-spec/Gen Agent Trust Hub

to-spec

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface by processing untrusted repository data to generate specifications.
  • Ingestion points: Instructions in SKILL.md direct the agent to explore the repository codebase and synthesize conversation history.
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the ingested codebase files.
  • Capability inventory: In SKILL.md, the agent is given the capability to read the repository and write to an external issue tracker; the inclusion of the ready-for-agent label specifically facilitates a multi-step chain (8b) where the generated output becomes input for subsequent agent tasks.
  • Sanitization: Absent; no validation or sanitization of the codebase content is required before it is published to the issue tracker.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 04:31 AM
Security Audit — agent-trust-hub — to-spec