skill-writer
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to use shell commands such as
mkdirto set up the directory structure for new skills. This behavior is expected for a developer tool and is confined to the specific scope of skill creation. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user requirements and project details to generate documentation and instructions for other skills. This creates a potential attack surface where malicious user input could be propagated into the generated skill's prompts.
- Ingestion points: User-provided descriptions and specifications for new skills.
- Boundary markers: The templates provided in the instructions use standard Markdown formatting but do not include specific delimiters or warnings to ignore potentially malicious instructions in the user-supplied content.
- Capability inventory: The skill is designed to perform file system operations, including directory creation and file writing.
- Sanitization: There is no mention of sanitizing or validating user input before it is used to generate the new skill's content.
Audit Metadata