ponytail-audit

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its requirement to ingest and process an entire codebase, which consists of untrusted data.
  • Ingestion points: The skill instructions in SKILL.md define a workflow to scan the whole tree and perform a whole-repo audit.
  • Boundary markers: The skill contains an explicit Boundaries section that scopes the task to over-engineering and strictly prohibits applying fixes or addressing other issues like security.
  • Capability inventory: No custom scripts or tools are provided within the skill; it utilizes the host agent's native file-reading capabilities.
  • Sanitization: The instructions do not specify any validation or sanitization protocols for the data being read from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 01:43 PM
Security Audit — agent-trust-hub — ponytail-audit