perplexity-known-pitfalls

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides defensive programming advice, such as warning against non-existent packages and recommending environment variables for API keys. It does not perform dangerous operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is an auditing tool that ingests external codebase files, creating a potential surface for indirect prompt injection. 1. Ingestion points: Reads files via the Read and Grep tools (SKILL.md). 2. Boundary markers: The skill does not define specific delimiters for audited data. 3. Capability inventory: Limited to read-only tools (Read, Grep). It has no network, write, or execution capabilities. 4. Sanitization: No sanitization is performed on the data being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 09:39 PM
Security Audit — agent-trust-hub — perplexity-known-pitfalls