customer-win-back-sequencer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality relies on ingesting and processing untrusted data from multiple external sources, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Processes user-provided CSV files (churn list) and external content fetched from the web, including news articles, LinkedIn profile data, and competitor reviews from platforms like G2.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to treat external content as data rather than instructions (e.g., no 'ignore embedded instructions' warnings).
- Capability inventory: The skill has the capability to write files to the local directory (e.g.,
clients/<client-name>/...) and can potentially trigger automated email campaigns through tools likesetup-outreach-campaign. - Sanitization: There is no evidence of sanitization, filtering, or validation of external data before it is interpolated into the prompts used to generate outreach sequences and reports.
Audit Metadata