gtm-competitive-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external file (../../profiles/client-profile.md) to populate the competitive strategy and battlecard sections. This creates a surface where malicious or unintended instructions embedded within the profile data could influence the agent's behavior during the strategy generation process.
  • Ingestion points: ../../profiles/client-profile.md (read via context loading instructions in SKILL.md).
  • Boundary markers: The skill uses {Client Profile: X} placeholders to denote where external data is inserted, but it lacks explicit safety instructions to the agent to ignore or sanitize embedded commands within that data.
  • Capability inventory: The skill possesses capabilities for markdown generation, HTML generation, and script-based PDF generation.
  • Sanitization: No sanitization or validation logic is defined for the imported client profile content.
  • [DYNAMIC_EXECUTION]: The skill documentation indicates support for generating output as a PDF using "Python + reportlab". This typically requires the agent to generate and execute a Python script at runtime to produce the document.
  • Evidence: The Artifact Generation section in SKILL.md specifies Option C: PDF — Python + reportlab.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:19 PM
Security Audit — agent-trust-hub — gtm-competitive-strategy