02-campaign-brief-global
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation template for marketing strategy. It does not contain executable scripts, shell commands, or network-enabled operations.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting external data from user inputs and local files to generate its output.
- Ingestion points: User answers to the information gathering questionnaire and content from the
.agents/product-marketing-context-global.mdfile. - Boundary markers: The skill does not employ specific delimiters or instructions to ignore potential commands embedded in the ingested data.
- Capability inventory: No capabilities for file system modification, network communication, or subprocess execution are present in the skill.
- Sanitization: There is no evidence of input filtering, escaping, or validation of the ingested content.
Audit Metadata