skills/metroscope-dev/skills/to-spec/Gen Agent Trust Hub

to-spec

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill synthesizes user conversation history into a technical specification that is subsequently published to an issue tracker, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: The skill is instructed to take the "current conversation context" as input for synthesis (SKILL.md).
  • Boundary markers: Absent. There are no explicit delimiters or instructions to treat the conversation context as untrusted data.
  • Capability inventory: The skill has the capability to explore the repository and publish content to an external issue tracker (SKILL.md).
  • Sanitization: Partially mitigated by a requirement to "Check with the user that these seams match their expectations" before final publishing, though no automated sanitization or filtering of the conversation content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:17 AM
Security Audit — agent-trust-hub — to-spec