confluence
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides capabilities to ingest untrusted data from external sources and perform actions based on that data.
- Ingestion points: The skill provides instructions for querying the Confluence Cloud REST API for page content (SKILL.md).
- Boundary markers: The provided examples do not include delimiters or instructions to ignore embedded prompts within the retrieved content.
- Capability inventory: The skill includes Python scripts and curl commands for creating and updating pages (
requests.post,curl -X POST), which could be abused if the agent obeys instructions found within the pages it reads. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from external pages before processing.
Audit Metadata