signup
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external playbook for RevOps inbound routing.
- Evidence: A link to a markdown file on GitHub is provided in
SKILL.md:https://github.com/coreyhaines31/marketingskills/blob/main/skills/revops/references/inbound-routing.md. - [INDIRECT_PROMPT_INJECTION]: The skill includes an "Initial Assessment" step that directs the agent to read local marketing context files, which serves as a potential surface for indirect instructions.
- Ingestion points: The instructions in
SKILL.mdspecify reading.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md. - Boundary markers: No specific delimiters or safety warnings are provided for processing the content of these context files.
- Capability inventory: The skill's primary function is providing optimization recommendations and audits; it does not contain capabilities for subprocess execution, file writing, or system modification.
- Sanitization: There is no mention of sanitizing or validating the contents of the ingested files.
Audit Metadata