political-scientist-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided political events, which serves as an ingestion point for untrusted data. The instructions lack explicit boundary markers or sanitization to protect against malicious instructions that could be embedded in the event descriptions.\n
- Ingestion points: The analytical process defined in
SKILL.md(Step 1) begins with defining the user-provided event.\n - Boundary markers: Absent; the instructions do not use delimiters or specify that the agent should ignore instructions found within the event data.\n
- Capability inventory: The skill consists entirely of markdown documentation and contains no scripts, binaries, or tool-access configurations, limiting the impact of any potential injection.\n
- Sanitization: Absent; no input validation or filtering is performed on the provided event data.\n- [EXTERNAL_DOWNLOADS]: The skill references a wide range of external academic and informational sources for theoretical reference.\n
- Evidence: Links to Wikipedia, the Stanford Encyclopedia of Philosophy, Cambridge University Press (APSR), and the American Political Science Association (APSA) are included. All referenced sources are established academic or informational entities.\n- [NO_CODE]: The skill is purely informational and instructional, containing no code (Python, Node.js), shell scripts, or binary files.
Audit Metadata