review-skill-sflabs
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform existence checks on standard directory paths to identify bundled platform skills and prevent naming collisions.
- [EXTERNAL_DOWNLOADS]: It fetches the latest list of bundled platform skills from official vendor documentation at docs.snowflake.com to ensure the audit uses current data.
- [PROMPT_INJECTION]: The skill ingests untrusted markdown and YAML files from local directories for auditing. It lacks explicit boundary markers to delimit this external content, which could facilitate indirect prompt injection attacks. This risk is partially mitigated by the requirement for explicit human confirmation before the agent performs any automated edits or file creations.
Audit Metadata