apply-sop-writer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform web searches for official PhD program or call pages to identify themes and specializations. This introduces a surface for indirect prompt injection, as an attacker could place malicious instructions on a website that the agent might visit during this research phase.
- Ingestion points: The agent is directed in
SKILL.mdto "search the web for the programme's or call's official page" to extract the declared scope. - Boundary markers: There are no instructions in the skill for the agent to use delimiters or safety warnings (e.g., "ignore embedded instructions") when processing the retrieved web content.
- Capability inventory: The agent utilizes web search and text generation/review capabilities.
- Sanitization: The skill does not prescribe any sanitization or validation techniques for the external data before it is interpolated into the agent's context.
Audit Metadata