11labs

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data which could contain malicious instructions.
  • Ingestion points: The skill explicitly prompts for a 'URL to fetch (use WebFetch)' or a 'file path to read' in the 'Before Starting' section of SKILL.md.
  • Boundary markers: No explicit instructions are provided to the agent to ignore or delimit potentially malicious instructions embedded within the fetched source content.
  • Capability inventory: The skill uses WebFetch and file system read tools. It does not contain subprocess calls, network write operations, or dynamic code execution (eval/exec).
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the content retrieved from external URLs or files before it is processed into the script format.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — 11labs