skills/naimsolong/ai-software-agency/specialist-marketing-ai-citation-strategist/Gen Agent Trust Hub
specialist-marketing-ai-citation-strategist
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the Agent tool to spawn subagents and incorporates user input directly into the prompt via the '{the user's question}' placeholder. This interpolation lacks delimiters, which could allow a malicious user input to influence or override the subagent's instructions.
- Ingestion points: User input is ingested via the prompt string of the Agent tool call in SKILL.md.
- Boundary markers: No explicit delimiters (such as XML tags or unique separators) or 'ignore embedded instructions' warnings are used to isolate the user input.
- Capability inventory: The skill is configured to spawn subagents and define their operational parameters.
- Sanitization: There is no logic present to sanitize or validate the user-provided text before it is inserted into the prompt template.
Audit Metadata