skill-upgrader

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run uv run python scripts/ragie_query.py to query a RAG system for academic references. This command execution is required for the skill's primary function of upgrading skill formats. \n- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by ingesting untrusted data from existing skill files. \n
  • Ingestion points: The content of the file at {path_to_skill} is read and provided to sub-agents. \n
  • Boundary markers: The skill does not employ delimiters or specific instructions to isolate the ingested text from the sub-agent instructions. \n
  • Capability inventory: The sub-agents have access to tools including Bash, Task, and Write. \n
  • Sanitization: No input validation or content filtering is implemented for the data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:04 AM
Security Audit — agent-trust-hub — skill-upgrader