highlight-action-items
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's 'Pattern 1: The Top-Loaded Executive Action Directive' accepts external content through an unformatted placeholder.
- Ingestion points: The
[INSERT TEXT]placeholder inSKILL.mdis intended to receive external project notes or logs. - Boundary markers: The template does not utilize delimiters (such as XML tags or Markdown separators) to isolate the untrusted input from the agent's instructions.
- Capability inventory: No risky capabilities (subprocess execution, network operations, or file system writes) are present in the skill.
- Sanitization: There are no instructions for sanitizing or escaping the input text, which could allow embedded instructions in the processed data to influence the AI's output structure.
Audit Metadata