shortform-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of strategy guidelines and technical specifications for video production. No malicious patterns, obfuscation, or unauthorized access attempts were detected during the analysis.\n- [NO_CODE]: There are no executable scripts, binary files, or external package installations included with the skill. All instructions are provided in plain markdown.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a workflow that involves analyzing user-provided video timeline data, creating a surface for potential indirect prompt injection.\n
- Ingestion points: External video timeline content and associated metadata processed by the agent (SKILL.md).\n
- Boundary markers: The instructions do not define specific delimiters to isolate external data from the agent's prompt context.\n
- Capability inventory: Usage of domain-specific tools
reframeAutoandaddCaptionsfor video manipulation.\n - Sanitization: No explicit content sanitization or validation logic is present in the skill instructions.
Audit Metadata