dbs-hook

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions and persona-based logic. No malicious code, external dependencies, or sensitive resource accesses were identified.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted user-supplied video scripts.
  • Ingestion points: Phase 1 of the workflow in SKILL.md requests the user to submit video scripts for diagnosis.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for the user-provided data.
  • Capability inventory: No dangerous capabilities (such as filesystem access, network requests, or tool execution) are associated with this skill.
  • Sanitization: No input validation or sanitization is performed on the user content.
  • [NO_CODE]: The skill does not provide or execute any scripts, binaries, or configuration files, operating solely through Large Language Model prompting.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 01:39 PM