meridian-investor-research

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingest and processes untrusted data from external websites. An attacker could place malicious instructions on a startup's website to manipulate the agent's behavior.
  • Ingestion points: The web_fetch operation in Step 1 of SKILL.md reads content from a user-provided or inferred startup_url.
  • Boundary markers: There are no instructions or delimiters specified to help the agent distinguish between data and instructions within the fetched content.
  • Capability inventory: The skill utilizes web_fetch and web search capabilities, and generates personalized text output based on the findings.
  • Sanitization: No sanitization, filtering, or validation of the external content is performed before it is used to influence the agent's output.
  • [COMMAND_EXECUTION]: The skill uses the web_fetch and web search tools to gather information about startups and investors based on user-supplied input.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:31 PM