skill-share
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the creation of content (skill files and Slack posts) based on user-provided names and descriptions. This presents a surface for indirect prompt injection where untrusted user input is propagated to other team members or files.
- Ingestion points: User-provided skill names, descriptions, and metadata in SKILL.md.
- Boundary markers: None identified; user input is directly interpolated into file templates and Slack message blocks.
- Capability inventory: Directory/file creation, ZIP archive generation, and network messaging via Slack tools (SLACK_SEND_MESSAGE, SLACK_POST_MESSAGE_WITH_BLOCKS).
- Sanitization: No explicit validation or sanitization of user-provided strings is mentioned in the documentation to prevent injection or directory traversal.
Audit Metadata