sus-audit
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to "Run safe checks for dynamic claims" and record exact commands and outputs. This implies the execution of shell commands to verify the behavior of the code being audited.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data including source code, tests, and configuration files, creating a surface for indirect prompt injection.
- Ingestion points: The agent accesses local files, configuration, and runtime wiring for inspection (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or headers to isolate audited content from the agent's instruction context.
- Capability inventory: The skill has the ability to execute shell commands and perform file system operations, including writing artifacts to
~/.agents/artifacts/and deleting/moving files during the close phase (SKILL.md). - Sanitization: No specific sanitization or filtering logic is described for handling content extracted from the audited source code.
Audit Metadata