specialist-marketing-short-video-editing-coach

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided content via the {the user's question} placeholder into a subagent prompt without security boundaries.
  • Ingestion points: User input is ingested into the subagent definition within SKILL.md.
  • Boundary markers: None (e.g., XML tags or delimiters) are present to isolate user content from system instructions.
  • Capability inventory: The skill uses the Agent tool to spawn ephemeral subagents.
  • Sanitization: No validation, escaping, or filtering is applied to the untrusted user input before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-marketing-short-video-editing-coach