skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system and repository operations using
mkdir,git diff, andgrep. These commands are used to manage the directory structure and verify that metadata versions are updated according to semantic versioning rules. - [INDIRECT_PROMPT_INJECTION]: The verification process involves the agent reading and interpreting the output of
git diff. This introduces a surface where malicious content embedded in the diff of a skill file could attempt to influence the agent's logic. - Ingestion points: The output of shell commands like
git diff --name-onlyandgit diff HEAD. - Boundary markers: No delimiters or safety instructions are provided to distinguish the diff data from the agent's instructions.
- Capability inventory: The agent has capabilities for command execution (
git,mkdir,npx) and file modification. - Sanitization: There is no sanitization of the diff output; the agent is simply instructed to search for version strings within the raw output.
Audit Metadata