campaign-canon
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and benchmark user-provided 'creative concepts' against its historical database. While this creates a surface for indirect prompt injection, it is restricted to the intended strategic analysis purpose of the skill.
- Ingestion points: User input provided during benchmarking sessions (as defined in
SKILL.md). - Boundary markers: Not explicitly present in the analyzed files.
- Capability inventory: None. The skill's primary function is data lookup and analysis; it does not execute shell commands or perform network operations in its provided configuration.
- Sanitization: Not applicable for the provided data files.
- [NO_CODE]: The analyzed portion of the skill consists entirely of Markdown case studies, indices, and YAML metadata. No executable code, shell scripts, or binary files were present.
- [SAFE]: All external URLs reference legitimate industry award platforms (D&AD, Cannes Lions) or reputable media hosting services (YouTube, Vimeo). No patterns associated with data exfiltration or credential theft were found.
Audit Metadata