pestle-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates untrusted external input by placing the $ARGUMENTS variable directly into its core instructions.
  • Ingestion points: The variable $ARGUMENTS is used in the instruction block within SKILL.md ("You are a strategic analyst conducting a PESTLE analysis for $ARGUMENTS").
  • Boundary markers: None. The user-provided content is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
  • Capability inventory: The skill does not define specific tools in its frontmatter, nor does it include executable scripts or file-system operations; it relies on the agent's default capabilities.
  • Sanitization: No filtering, escaping, or validation is applied to the $ARGUMENTS input before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:02 PM
Security Audit — agent-trust-hub — pestle-analysis