api-confluence-integration

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the processing of external architectural specifications which represents an indirect prompt injection surface. Ingestion points include user-provided spec drafts (SKILL.md), while capability inventory includes interfacing with the confluence_api. There are no explicit boundary markers or sanitization steps mentioned to prevent embedded instructions in the source text from influencing the agent's behavior during conversion or API interaction.
  • [DATA_EXFILTRATION]: The primary function of the skill is to push formatted specifications to the Confluence REST API. This functional requirement creates a data egress point where sensitive internal architectural details could be transmitted to an external service. Users should ensure the confluence_api tool is properly scoped and governed.
  • [NO_CODE]: The skill consists entirely of markdown documentation and natural language instructions. No scripts, binaries, or executable code sections were found within the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 08:36 PM
Security Audit — agent-trust-hub — api-confluence-integration