skills/swn94/awesome-legal-skills/requete-cph-licenciement-faute-grave-selim-brihi/Gen Agent Trust Hub
requete-cph-licenciement-faute-grave-selim-brihi
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection as it ingests untrusted user-supplied facts and employer motifs for document generation. -- Ingestion points: Interactive user dialogue in Phase 1 (SKILL.md). -- Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are present. -- Capability inventory: File system access for .docx creation and file movement. -- Sanitization: Absent; user input is interpolated directly into the drafting process.
- [DATA_EXFILTRATION] (SAFE): The skill collects a high volume of PII (Name, DOB, Address, Salary). This is justified by the primary purpose of drafting legal forms. No unauthorized network requests or access to local credentials (e.g., SSH keys) were detected.
- [NO_CODE] (SAFE): The skill consists of markdown instruction files and reference data; it does not include executable scripts, shell commands, or external package dependencies.
Audit Metadata