ecc-recipes
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a bash script to be executed by the agent to locate and list command files (.md) within the user's local directory (specifically
~/.claude/plugins/and related paths). This is used to build a dynamic catalog of available commands. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input in the form of workflow descriptions to provide recommendations.
- Ingestion points: The user-provided workflow description argument in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters are defined for the user-supplied text.
- Capability inventory: The skill utilizes shell commands (
find,basename,sort) to list files and provides advisory workflow plans to the user. - Sanitization: No sanitization or validation logic is present for the user-supplied workflow description.
Audit Metadata