marketing-ideas

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by instructing the agent to read marketing context and strategy files from the local environment.
  • Ingestion points: The agent is directed to read .agents/marketing-strategy.md, .agents/marketing-learnings.md, .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md for background information.
  • Boundary markers: There are no explicit instructions to the agent to treat the contents of these project files strictly as data or to ignore any potential instructions embedded within them.
  • Capability inventory: The skill is informational and does not define any executable code, shell command tools, or network exfiltration capabilities.
  • Sanitization: No validation, sanitization, or filtering logic is prescribed for the content ingested from these local files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 09:00 PM