studio-develop-prd-roadmap

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows standard procedures for a technical product lead assistant. It focuses on local document analysis and provides integration recommendations for well-known services like Stripe, PostHog, and Sentry. No signs of malicious behavior, obfuscation, or credential exfiltration were detected.- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from user-provided files such as docs/PRODUCT.md and docs/DESIGN.md to generate its outputs. This creates a potential surface for indirect prompt injection, although this behavior is fundamental to the skill's primary purpose.
  • Ingestion points: The skill reads from docs/PRODUCT.md, docs/DESIGN.md, and several files within the productos/ directory.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent instructions.
  • Capability inventory: The skill is restricted to file system read and write operations for documentation purposes.
  • Sanitization: There is no evidence of filtering or escaping the content of ingested files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:33 PM
Security Audit — agent-trust-hub — studio-develop-prd-roadmap