skills/peterbamuhigire/social-media-skills/marketing-foundations-stp-positioning/Gen Agent Trust Hub
marketing-foundations-stp-positioning
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer feedback, enquiry logs, and CRM data for marketing analysis.
- Ingestion points: Customer evidence including sales records, CRM exports, reviews, and interviews are consumed by the agent as specified in
SKILL.mdandreferences/customer-insight-and-value-themes.md. - Boundary markers: The skill instructs the agent to label insights with sources and confidence levels, but it lacks specific technical delimiters or warnings to ignore instructions embedded within customer-supplied text.
- Capability inventory: The skill defines its boundaries as 'read and search only' and 'read-only analysis', explicitly prohibiting publishing or live account changes without specific client authority (
SKILL.md). - Sanitization: There are no documented procedures for sanitizing or escaping customer-supplied content before it is processed by the language model.
Audit Metadata