skill-share

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for generating new skill files (SKILL.md) and metadata based on user-provided inputs (name, description).
  • Ingestion points: Untrusted data enters the agent context through user-provided skill names and descriptions used to populate new SKILL.md files.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content within the generated skill metadata are documented.
  • Capability inventory: The skill possesses file system write capabilities (creating directories and files), packaging capabilities (zip compression), and network capabilities (Slack messaging via Rube).
  • Sanitization: The documentation does not specify sanitization or validation of the input text before it is interpolated into the generated skill files.
  • [SAFE]: The network operations documented (Slack messaging via Rube) target a well-known service for legitimate team collaboration purposes and do not involve sensitive local file access or exfiltration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:56 PM
Security Audit — agent-trust-hub — skill-share