skills/compasify/skills/confluence/Gen Agent Trust Hub

confluence

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: Scripts scripts/confluence_api.py and scripts/confluence_auth.py perform aggressive discovery of authentication tokens by reading configuration files from multiple applications, including Cursor, Claude Desktop, Windsurf, and VS Code extensions like Cline and Roo.
  • [CREDENTIALS_UNSAFE]: Both scripts/download_confluence.py and scripts/confluence_api.py explicitly disable SSL certificate verification (verify=False and ssl.CERT_NONE), which can expose sensitive Personal Access Tokens (PATs) to interception.
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/mermaid_renderer.py and scripts/render_mermaid.py to execute the external mmdc (Mermaid CLI) tool for diagram rendering.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. 1. Ingestion points: scripts/download_confluence.py fetches untrusted page content via the Confluence API. 2. Boundary markers: No delimiters or safety instructions are used to wrap the downloaded content. 3. Capability inventory: The skill can execute shell commands and make network requests. 4. Sanitization: Downloaded content is not sanitized before being returned to the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:48 PM