pestel-delta-monitor

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as credential theft, privilege escalation, or persistence mechanisms were found.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference to a GitHub repository (github.com/deanpeters/product-manager-prompts) in the references section. This is a vendor-owned resource used for documentation and attribution.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it processes untrusted user data (prior PESTEL reports). However, it includes mitigating instructions such as requiring real URLs for all data, following a search-plan gate, and enforcing a 'do-not-invent' list for regulations and statistics.
  • Ingestion points: Prior PESTEL analysis provided via pasted text or attached files (SKILL.md).
  • Boundary markers: Mentions an ARGUMENTS: line for input but does not specify strict XML or character-based delimiters for the external content.
  • Capability inventory: The skill is designed to trigger investigations and searches for regulatory and statistical data (implied browsing tools).
  • Sanitization: Not explicitly mentioned, though the 'do-not-invent' rule acts as a validation layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:10 PM
Security Audit — agent-trust-hub — pestel-delta-monitor