confluence-property

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes confluence CLI commands to interact with the Confluence REST API. This is the primary and intended function of the skill for managing metadata.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it retrieves data (properties) from Confluence that could be modified by third parties to include instructions. This is a common characteristic of tools processing external data.\n
  • Ingestion points: Confluence property values retrieved via confluence property get and confluence property list (SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the retrieval logic.\n
  • Capability inventory: confluence property set, confluence property delete, and confluence search cql (SKILL.md).\n
  • Sanitization: No explicit sanitization or validation of the retrieved property content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 07:14 PM
Security Audit — agent-trust-hub — confluence-property