project-knowledge

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external platforms (Jira and Confluence) which are common surfaces for indirect prompt injection if those sources contain untrusted content.
  • Ingestion points: The skill searches Jira issues and Confluence pages for project context as defined in SKILL.md.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions found within the retrieved data.
  • Capability inventory: The skill has the ability to write summarized findings to the Blinko note-taking tool.
  • Sanitization: The instructions do not specify a requirement for sanitizing the external data before it is summarized or persisted.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 02:59 AM
Security Audit — agent-trust-hub — project-knowledge