skills/h-mmer/pentest-agents/surface/Gen Agent Trust Hub

surface

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by passing untrusted user input into sub-agent instructions.
  • Ingestion points: User input from $ARGUMENTS is ingested and used to build the prompt for the recon-ranker agent in SKILL.md.
  • Boundary markers: There are no delimiters or boundary markers used to separate user-provided arguments from the agent's instructions.
  • Capability inventory: The skill possesses the ability to read local data from the recon/ directory and a brain data store, and it can trigger other agents (recon-ranker, /hunt).
  • Sanitization: No sanitization or validation is applied to the input before it is interpolated into the agent prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 07:58 AM
Security Audit — agent-trust-hub — surface