investigating-a-codebase
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for the agent to ingest and analyze external codebase content using discovery and read tools.
- Ingestion points: The agent is instructed to read entry points, index files,
package.json, and configuration files across the target codebase (SKILL.md). - Boundary markers: There are no instructions for using delimiters or explicit "ignore embedded instructions" warnings when processing the content of these files.
- Capability inventory: The skill leverages
Read,Glob, andGreptools to explore file structure and content. - Sanitization: The instructions do not include requirements for sanitizing or escaping the data retrieved from the codebase before it is incorporated into the agent's context, potentially allowing malicious files to influence subsequent agent actions.
Audit Metadata