product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it reads and processes untrusted data from the local codebase (e.g., README, marketing copy, package.json) to auto-draft marketing context.
  • Ingestion points: Files such as README, package.json, and other documentation are read to extract product information as specified in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from following malicious instructions that might be embedded within the scanned files.
  • Capability inventory: The skill performs file read operations on the codebase and file write operations to .agents/product-marketing-context.md.
  • Sanitization: There is no evidence of content sanitization or validation performed on the data ingested from the repository before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 11:22 PM
Security Audit — agent-trust-hub — product-marketing-context