free-tool-strategy

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by instructing the agent to ingest content from files within the user's project environment.
  • Ingestion points: The skill instructions in SKILL.md, SKILL.en.md, and SKILL.es.md command the agent to read .claude/product-marketing-context.md if it exists.
  • Boundary markers: The instructions lack delimiters or specific warnings to ignore potential commands embedded within the ingested data.
  • Capability inventory: Analysis of the skill's files confirms it contains no executable code, subprocess tools, network capabilities, or file-writing logic.
  • Sanitization: No validation or sanitization protocols are specified for the contents of the context file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:59 AM
Security Audit — agent-trust-hub — free-tool-strategy