upsell-and-expansion
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process unstructured external data, such as CSM notes, meeting transcripts, and PDFs, creating a surface for indirect prompt injection. Ingestion points: Workflow Step 1 in SKILL.md and Rule 1 in references/input-rules.md (processing user-provided dumps and uploads). Boundary markers: SKILL.md contains a mandatory 'Untrusted content' section instructing the agent to treat all external text as data, not instructions. Capability inventory: The skill enables the agent to generate text reports, save files (documents, decks, sheets), and interact with search tools. Sanitization: The instructions mandate that the agent explicitly declare when it has ignored instructions embedded within untrusted data.
- [NO_CODE]: The skill folder consists solely of Markdown instructional and reference files. No scripts, binaries, or external package dependencies (Python/Node.js) are present.
Audit Metadata