skill-share
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of agent skill packages and Slack announcements based on user-provided skill names and descriptions. This introduces a surface where malicious instructions could be embedded into the generated documentation or shared summaries to influence other users or agents.\n
- Ingestion points: User-provided skill names and descriptions used to populate generated SKILL.md files and Slack messages.\n
- Boundary markers: The skill does not explicitly define the use of delimiters or instructions to ignore embedded commands in the generated content.\n
- Capability inventory: File system write access, directory creation, archiving (zip), and network messaging via the Rube Slack integration (SKILL.md).\n
- Sanitization: While naming conventions and metadata completeness are checked, there is no mention of sanitizing or escaping the content for potential injection strings.
Audit Metadata