ahrefs
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing the
@useclawlink/clitool via shell commands (npx) to authenticate, connect services, and run SEO analytics actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from Ahrefs (backlinks, keyword overviews, site audits), which represents an external data ingestion surface.
- Ingestion points: Data is brought into the agent context via the output of actions like
ahrefs_fetch_all_backlinksandahrefs_retrieve_organic_keywordsinSKILL.md. - Boundary markers: The instructions advise the agent to confirm with the user before performing write actions, but no specific boundary markers or delimiters are defined for handling the ingested text data.
- Capability inventory: The skill has the capability to execute shell commands via
npxand access the local filesystem at~/.clawlink/(referenced inSKILL.md). - Sanitization: There is no evidence of data sanitization or filtering applied to the external Ahrefs content before it is processed by the agent.
Audit Metadata