google-developer-knowledge
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses simple bash scripts (
search_docs.sh,get_document.sh, andbatch_get_documents.sh) to perform its tasks. These scripts primarily usecurlto communicate with the Developer Knowledge API. - [EXTERNAL_DOWNLOADS]: The scripts download documentation content from
developerknowledge.googleapis.com. This is an official Google service, and the downloads are performed for the stated purpose of documentation retrieval. - [INDIRECT_PROMPT_INJECTION]: The skill ingests documentation content from an external source, which represents a potential surface for indirect prompt injection if the retrieved content were to contain malicious instructions.
- Ingestion points: Documentation content is retrieved from
developerknowledge.googleapis.comvia API calls in all three provided scripts. - Boundary markers: The scripts do not wrap the retrieved content in specific delimiters or provide explicit instructions to the agent to ignore embedded commands.
- Capability inventory: The skill possesses network access capabilities (via
curl) and file-write capabilities (via the--outputflag in the scripts). - Sanitization: The scripts output the raw JSON response from the API without performing sanitization or filtering of the content.
Audit Metadata