The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation, identity definitions, and analytical frameworks. There are no scripts (Python, JavaScript, Shell) or binaries included in the skill package.
[SAFE]: No patterns associated with prompt injection, data exfiltration, obfuscation, or privilege escalation were detected. The instructions focus on establishing a senior policy analyst persona and defining rigorous methodology for evidence-based research.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process untrusted data (policy briefs, news, reports) for analysis, it lacks any high-risk capabilities such as network access, file system writes, or subprocess execution that could be exploited via injection. The risk is negligible.

policy-analyst