securite-anssi
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the local filesystem by creating an 'audits/' directory and writing Markdown report files (e.g.,
audits/securite-anssi-YYYY-MM-DD.md). This behavior is explicitly defined and necessary for the skill's primary function of documenting audit findings. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes untrusted data from the user's project files during the auditing process.
- Ingestion points: Project source code, configuration files, infrastructure-as-code, and CI/CD pipeline definitions.
- Boundary markers: The skill does not explicitly define delimiter markers to isolate untrusted project content from its internal audit instructions.
- Capability inventory: The skill has the capability to read project files, create directories, and write new files to the filesystem.
- Sanitization: There is no explicit sanitization of the project content being audited, though the use of a structured audit checklist acts as a constraint on how the agent interprets the data.
Audit Metadata