Skills
skills/roger-235/my_skill_repo/marketing-ideas/Gen Agent Trust Hub

marketing-ideas

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates a surface for indirect prompt injection by instructing the agent to ingest data from an external local file to tailor its marketing recommendations.
  • Ingestion points: The file .claude/product-marketing-context.md is read at startup if it exists (defined in SKILL.md).
  • Boundary markers: There are no explicit delimiters or system instructions provided to the agent to treat the content of the context file as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill is primarily designed for text-based strategic advice; analysis of the provided files (SKILL.md, README.md, references/ideas-by-category.md) shows no use of shell execution, network exfiltration tools, or file-writing capabilities.
  • Sanitization: No sanitization or validation logic is defined for the content loaded from the context file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — marketing-ideas