skill-share
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a template engine that takes user input (skill name, description) and interpolates it into generated files and Slack messages. This is the primary function of the skill and does not appear to be used maliciously.
- Ingestion points: User-provided skill metadata during initialization in SKILL.md.
- Boundary markers: The skill uses YAML frontmatter and structured directory patterns to isolate metadata.
- Capability inventory: File system write access for skill creation and Slack messaging tools (SLACK_SEND_MESSAGE, SLACK_POST_MESSAGE_WITH_BLOCKS) for notifications.
- Sanitization: The skill description explicitly mentions validation of structure, naming conventions (hyphen-case), and metadata completeness before packaging.
- [COMMAND_EXECUTION]: The skill performs routine administrative tasks such as creating directories, generating files, and packaging assets into zip files. These operations are limited to the skill's stated purpose of development automation.
Audit Metadata