marketing-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading project-specific context files, creating a potential surface for indirect instructions to be processed by the agent.\n
  • Ingestion points: The skill directs the agent to read data from strategy/brand.md, about/me.md, content/ideas.md, and content/calendar.md (SKILL.md).\n
  • Boundary markers: No explicit markers, delimiters, or warning instructions are provided to distinguish data from potentially malicious instructions within these files.\n
  • Capability inventory: The skill allows the agent to generate and write draft files to the content/ directory. No network access, arbitrary command execution, or sensitive file access capabilities are defined.\n
  • Sanitization: The instructions do not include any validation or sanitization steps for the content ingested from the workspace context files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:07 PM
Security Audit — agent-trust-hub — marketing-strategy