skill-share

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests user-provided text to generate executable AI instructions (SKILL.md files).
  • Ingestion points: The skill takes a name and description from the user in SKILL.md.
  • Boundary markers: There are no specified delimiters or instructions to prevent the agent from obeying instructions embedded within the user-provided name or description during the creation process.
  • Capability inventory: The skill performs file system operations (directory and file creation) and utilizes Slack tools (SLACK_SEND_MESSAGE, SLACK_POST_MESSAGE_WITH_BLOCKS) to distribute the resulting content.
  • Sanitization: The documentation does not describe any validation or escaping mechanisms to sanitize user input before it is interpolated into the generated skill templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:18 AM
Security Audit — agent-trust-hub — skill-share