skill-updater
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill is designed to ingest, read, and process content from external skill directories or .skill archives provided by the user.
- Ingestion points: The
analyze_skill.pyscript readsSKILL.mdfiles; the instructions direct the agent tocat <skill-path>/SKILL.mddirectly into the conversation context, andunziparchives to temporary directories. - Boundary markers: Absent. The instructions do not specify the use of XML tags or other delimiters to isolate the untrusted content from the agent's instructions, nor do they warn the agent to ignore instructions found within analyzed files.
- Capability inventory: The skill has the capability to execute shell commands (
bash,unzip,cat), run Python scripts (analyze_skill.py,quick_validate.py), and modify files on the local system. - Sanitization: Absent. There is no evidence of sanitization or filtering of the content read from external skill files before it is processed or displayed to the agent.
Audit Metadata