paul-graham-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection within its 'Paul Graham Perspective' workflow.
  • Ingestion points: The skill explicitly instructs the agent to use search tools (e.g., WebSearch) to gather external information about founders, markets, and products (SKILL.md, Step 2).
  • Boundary markers: There are no instructions for the agent to wrap external content in delimiters or use markers to separate untrusted search results from the system's core instructions.
  • Capability inventory: The skill utilizes tool-calling capabilities (WebSearch) and incorporates the results into the model's final response generation. It does not contain instructions for dangerous shell commands or sensitive file access.
  • Sanitization: The skill lacks any instructions for sanitizing, validating, or escaping data retrieved from the web before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 07:12 AM