standards-updates-tracker
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection via the 'content' parameter. Ingestion point: parameters['content'] in skill.py. Boundary markers: Absent. Capability inventory: Data processing and artifact naming only; no file-write, network, or subprocess calls detected. Sanitization: Absent. While capabilities are limited to returning data, malicious instructions within the framework text could influence downstream agent reasoning.
- [INFO] (INFO): The script contains a runtime error (NameError) because the variable 'skill_dir' is used in the 'execute' method but is never defined.
Audit Metadata