skills/eho/agent-skills/prd/Gen Agent Trust Hub

prd

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's behavior is consistent with its stated purpose. No malicious code, obfuscation, or privilege escalation attempts were found.- [DATA_EXFILTRATION]: The skill creates and writes Markdown files to the local 'tasks/' directory. No sensitive file access or external network communication was detected.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by incorporating user input into generated documents.
  • Ingestion points: User feature descriptions and clarifying question responses in SKILL.md.
  • Boundary markers: Absent; user input is directly interpolated into the PRD template.
  • Capability inventory: File creation and write access within the 'tasks/' folder.
  • Sanitization: None; user input is not escaped or validated before being written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 02:10 AM