skills/kelvinz/cobb/prd/Gen Agent Trust Hub

prd

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill is composed of Markdown instructions and a template. No scripts, binaries, or executable code are included in the package.
  • [Data Exposure & Exfiltration] (SAFE): The skill's scope is restricted to the local 'tasks/' and 'references/' directories. There is no evidence of network communication, hardcoded credentials, or access to sensitive system configuration files.
  • [Prompt Injection] (SAFE): The instructions include functional guardrails such as 'Do not implement code' and follow a structured workflow. No patterns of prompt injection, role-play bypass, or safety filter overrides were identified.
  • [Indirect Prompt Injection] (SAFE): While the skill ingests data from local project files, the risk is negligible due to the absence of high-risk capabilities like command execution or network access. (1) Ingestion points: tasks/memory.md and PRD files; (2) Boundary markers: absent; (3) Capabilities: limited to reading and writing local Markdown files; (4) Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 12:50 PM