search-company-knowledge
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- Internal Knowledge Retrieval: The skill uses integrated tools to search and fetch content from systems like Confluence and Jira. This behavior is consistent with its stated purpose of assisting with internal technical documentation and knowledge management.
- Content Processing Considerations: The skill processes information from internal documentation and tickets. As with any system that ingests text from external or user-generated sources, there is a potential for indirect prompt injection if those sources contain content designed to manipulate AI behavior.
- Ingestion points: Content is retrieved via tools such as search, getConfluencePage, and getJiraIssue defined in SKILL.md.
- Boundary markers: While the skill emphasizes synthesis and source attribution, it does not specify explicit boundaries or delimiters to isolate retrieved content from the agent's core instructions.
- Capability inventory: The skill's capabilities are scoped to data retrieval within the Atlassian environment and do not include arbitrary command execution or external network operations.
- Sanitization: No specific mechanisms for filtering or escaping retrieved text are mentioned in the instructions.
- Secure Configuration: No evidence of obfuscation, hardcoded credentials, unauthorized downloads, or persistence mechanisms was identified during the analysis.
Audit Metadata