skills/changhochien/oh-my-pi/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied task descriptions via an input argument without utilizing boundary markers or sanitization, creating a surface for indirect prompt injection. * Ingestion points: The skill accepts a task or feature description as a primary argument in SKILL.md. * Boundary markers: Absent; there are no delimiters or specific instructions to treat user input as untrusted data. * Capability inventory: The skill is limited to text generation and plan documentation, though it recommends the subsequent use of other tools like team or ralph skills. * Sanitization: Absent; no validation or escaping of the input string is performed.
  • [NO_CODE]: The skill is composed entirely of markdown instructions and templates and does not include any executable scripts, binaries, or software packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 02:23 AM
Security Audit — agent-trust-hub — plan