ask-peer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of markdown documentation and YAML frontmatter. No Python scripts, JavaScript files, or shell commands are included.
  • PROMPT_INJECTION (SAFE): The instructions define a specific persona for a subagent. No evidence of behavioral overrides, safety bypasses, or malicious system prompt extraction was found.
  • INDIRECT_PROMPT_INJECTION (SAFE): While the skill defines a surface for processing user-provided consultation requests (SKILL.md), it does not define any associated tools or scripts that could be exploited to perform file system or network operations. 1. Ingestion points: user consultation requests via /ask-peer. 2. Boundary markers: absent. 3. Capability inventory: none. 4. Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM