confluence-search

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the confluence command-line tool in SKILL.md to perform search operations, build queries interactively, and manage search history.
  • [DATA_EXFILTRATION]: Retrieval of Confluence content and its export to local CSV or JSON files using confluence search export are core functions of the skill; no unauthorized network exfiltration was detected.
  • [PROMPT_INJECTION]:
  • Ingestion points: Processes content from Confluence search results (page excerpts, titles, labels) in SKILL.md.
  • Boundary markers: None; the skill does not specify delimiters for data retrieved from Confluence.
  • Capability inventory: Includes the ability to execute confluence CLI commands and perform local file writes as described in SKILL.md.
  • Sanitization: No sanitization is performed on data retrieved from Confluence before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 07:14 PM
Security Audit — agent-trust-hub — confluence-search