confluence-expert

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by extracting and analyzing existing documentation. Ingestion points: 'Extract documentation for analysis' (SKILL.md). Boundary markers: No delimiters or instructions to ignore embedded commands are present. Capability inventory: Capabilities include space management, creating/updating/deleting pages, and configuring permissions (SKILL.md). Sanitization: No content validation or escaping logic is specified.
  • [NO_CODE]: No executable scripts, binary files, or external code dependencies are included in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 07:00 AM