ssotize
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various 'artifacts and platforms' during its audit phase. This ingestion surface is theoretically susceptible to indirect prompt injection if the files being audited contain malicious instructions aimed at influencing the agent's consolidation plan.
- Ingestion points: The skill reads local project files and content from external platforms as defined in the workflow (SKILL.md).
- Boundary markers: The skill implements a mandatory human-in-the-loop checkpoint, requiring the agent to present an audit report and obtain explicit approval before proceeding to the mutation phase (SKILL.md).
- Capability inventory: The skill has the capability to write to files and modify artifacts across platforms (SKILL.md).
- Sanitization: No specific input sanitization for LLM prompts is mentioned, relying instead on the user approval gate.
- [COMMAND_EXECUTION]: The instructions specify that structural code moves should be performed using 'language-aware tools or scripted AST/parser edits' rather than simple text replacement. This necessitates the execution of development tools and scripts within the local environment to ensure precise and safe modifications.
Audit Metadata