master-bp-review

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business plans and pitch decks which could potentially contain malicious instructions. However, the skill lacks high-risk capabilities like network access.
  • Ingestion points: Processes user-provided documents (BPs, pitch decks, memos) as mentioned in SKILL.md.
  • Boundary markers: No explicit instruction delimiters or 'ignore embedded instructions' directives are defined in the skill instructions.
  • Capability inventory: Utilizes file reading tools and local file writing to save review reports (e.g., bp-review-*.md).
  • Sanitization: No sanitization or validation of the input document content is specified.
  • [COMMAND_EXECUTION]: The skill performs file system write operations to save reports in the current working directory, which is consistent with its stated purpose of generating a review document.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 07:31 AM
Security Audit — agent-trust-hub — master-bp-review