confluence
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from external Confluence instances, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Content is ingested via API calls in
scripts/confluence.py(e.g.,get_page,search_content). - Boundary markers: There are no explicit delimiters or instructions to the agent to treat the retrieved Confluence content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill has the ability to make network requests (Confluence API) and write to the local file system (using the
--outputargument in thepage getcommand and when downloading attachments). - Sanitization: The skill performs Markdown conversion but does not sanitize or filter the content for potential injection strings before providing it to the agent.
Audit Metadata