investigate
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages Bash for environment interactions required for debugging, such as 'rm -rf' commands to clear build caches or running arbitrary test commands. These operations can lead to significant environment modification if misused.
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading and processing data from untrusted sources, creating a potential attack surface.
- Ingestion points: Untrusted data is ingested from error messages, stack traces, log files, and external search results from project issue trackers.
- Boundary markers: The instructions lack specific guidance on using delimiters or markers to separate untrusted debug data from the agent's core instructions.
- Capability inventory: The agent has access to arbitrary shell command execution (Bash), file system read/write access, and the ability to spawn sub-agents to analyze data.
- Sanitization: No explicit sanitization or filtering is performed on data retrieved from external logs or issue trackers before it is processed by the model.
Audit Metadata