whistleblower-policy-malik-taiar

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for Indirect Prompt Injection because its primary function involves auditing untrusted external documentation provided by the user. • Ingestion points: Documentation requested includes internal reporting procedures, communication materials, and templates (found in SKILL.md, Section 3). • Boundary markers: The instructions lack explicit boundary markers to differentiate between the agent's instructions and the content of the analyzed documents. • Capability inventory: The skill is limited to textual analysis and drafting; it lacks access to dangerous tools such as arbitrary shell command execution or network exfiltration. • Sanitization: There is no evidence of specific input sanitization or filtering for user-provided documentation.
  • [SAFE]: The skill only references official and trusted government or regulatory domains, such as legifrance.gouv.fr for French legislation and cnil.fr for data protection guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:17 AM