project-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase data (source code, configuration files, and documentation) to generate a summary. This creates a surface for indirect prompt injection where malicious instructions hidden in the analyzed files could potentially influence the agent's output or behavior.
- Ingestion points: Untrusted data enters the context through
list_directory,glob, and thecodebase_investigatortool as described inSKILL.md(Workflows 1-6). - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the agent when reading project files.
- Capability inventory: The skill possesses file-writing capabilities to generate
PROJECT_SUMMARY.mdas specified inSKILL.md(Workflow 7). - Sanitization: There is no evidence of sanitization, validation, or filtering of the content ingested from the external project files before it is processed by the agent.
Audit Metadata