privacy-policy

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because the workflow (Step 1) directs the agent to visit external product websites to gather data. This creates a vulnerability where a malicious website could contain hidden instructions designed to manipulate the agent's behavior or output.\n
  • Ingestion points: External product websites and URLs provided by the user in SKILL.md.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the developer's instructions and the external data it retrieves.\n
  • Capability inventory: The skill's capabilities are primarily focused on generating text-based legal documentation and compliance reports.\n
  • Sanitization: The skill does not include instructions for the agent to sanitize, escape, or validate the content retrieved from external websites before it is incorporated into the prompt context.\n- [NO_CODE]: This skill does not contain any executable scripts, binary files, or code-based logic; it consists entirely of descriptive markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 04:39 PM