retrieving-developer-knowledge
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- External Documentation Ingestion: The skill retrieves information from various developer documentation domains. This introduces a surface for indirect prompt injection, where content from these external sources could potentially influence the agent's behavior.
- Ingestion points: Content enters the context through MCP tools (search_documents, answer_query, get_documents) and REST API responses fetched via curl, as documented in SKILL.md and references/api-fallback.md.
- Boundary markers: The instructions do not specify the use of clear delimiters or markers to separate retrieved external content from the agent's primary instructions.
- Capability inventory: The skill possesses the capability to execute shell commands (curl, gcloud) and interact with remote tools to perform network operations.
- Sanitization: The instructions do not include specific steps for the agent to sanitize or filter external content before processing it.
- Authentication and Tool Execution: The skill instructs the agent to use shell commands such as gcloud and curl to manage authentication and interact with the Developer Knowledge API. This involves retrieving and passing bearer tokens and API keys to facilitate access to the requested documentation services.
Audit Metadata