link-building
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from third-party websites, mentions, and competitor pages during the link-prospecting phase.
- Ingestion points: The agent is instructed to read content from third-party sites identified through search operators or SEO tools (Ahrefs, Semrush, DataForSEO) to qualify prospects and understand mention context.
- Boundary markers: There are no explicit instructions or delimiters used to separate untrusted third-party content from the agent's internal instructions, nor are there warnings to ignore embedded commands in that data.
- Capability inventory: The skill utilizes network operations via external SEO tools and has the capability to generate outreach drafts based on the processed third-party content.
- Sanitization: No explicit sanitization or filtering of the third-party content is specified before it is used to populate outreach templates.
- Mitigation: The risk is significantly mitigated by the skill's explicit requirement that the agent must only draft outreach for user approval rather than sending it autonomously.
Audit Metadata