search-company-knowledge

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it retrieves and synthesizes untrusted data from external sources. * Ingestion points: Full content from Confluence pages and Jira issues is fetched in 'Step 3: Fetch Detailed Content'. * Boundary markers: The instructions lack explicit delimiters or 'ignore instructions' directives for the interpolated document content. * Capability inventory: The skill uses tools to search and retrieve documentation (search, searchConfluenceUsingCql, searchJiraIssuesUsingJql, getConfluencePage, getJiraIssue). * Sanitization: No specific sanitization or validation of the retrieved documentation content is implemented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:11 PM