persuasion-cialdini-influence-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the
$ARGUMENTSvariable inSKILL.mdto establish context for its persuasion design workflow. This creates a surface for indirect prompt injection where malicious instructions embedded in the input could attempt to subvert the agent's logic. While the skill's instructions emphasize ethics and traceability, the lack of explicit sanitization or delimiters for the injected context represents a structural vulnerability. • Ingestion points:$ARGUMENTSvariable inSKILL.md• Boundary markers: Absent (untrusted input is interpolated directly) • Capability inventory: Primarily text generation, analysis, and drafting; no file-system or network capabilities detected in the provided skill files. • Sanitization: Absent.
Audit Metadata