factory-spec

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from local project files, creating a potential surface for indirect prompt injection. This ingestion is central to the skill's primary function of product specification.
  • Ingestion points: The skill reads documentation from docs/factory/CONTRACT.md and docs/factory/CHARTER.md.
  • Boundary markers: No explicit delimiters are provided to the agent to differentiate documentation content from system instructions.
  • Capability inventory: The skill's capabilities are limited to reading files and facilitating interactive sessions; it does not possess network access, shell execution, or sensitive file access permissions.
  • Sanitization: No sanitization or validation is performed on the content ingested from local files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:41 PM
Security Audit — agent-trust-hub — factory-spec