codebase-search
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repositories which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill ingests content from files (source code, config, templates, metadata) using tools like
Read,Grep, andBashas described inSKILL.md(Step 4: Read winners). - Boundary markers: The instructions do not define delimiters or specific warnings to the agent to treat repository content as data only and to ignore any embedded instructions (e.g., instructions hidden in Markdown comments or documentation).
- Capability inventory: The skill possesses the
Bash,Read,Grep, andGlobtools, providing it with the capability to read any file in the workspace and execute shell commands to support its search logic. - Sanitization: There are no instructions requiring the agent to sanitize, escape, or validate the content retrieved from the files before it is used to generate search briefs or decide on the next skill to invoke (such as
debuggingorcode-refactoring).
Audit Metadata