collab-spec

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it handles untrusted data during document generation. It ingests user-defined product requirements and goals to produce output without using specific boundary markers or sanitization procedures.\n
  • Ingestion points: User inputs regarding product/function goals, team information, and existing materials processed in SKILL.md and references/product-manager.md (Phase 1).\n
  • Boundary markers: The instructions lack explicit delimiters (e.g., XML tags, triple quotes) to isolate user-provided data from the system's generation logic.\n
  • Capability inventory: The skill possesses file-writing capabilities, specifically managing files within a _workspace/ directory as outlined in references/product-manager.md.\n
  • Sanitization: There are no documented steps for escaping or validating external content before it is interpolated into the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — collab-spec