third-party-cookies
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill includes diagnostic commands that perform network operations to external domains for header analysis.\n
- Evidence: The
curl -sI https://tracker.example.com/pixel.gifcommand inreferences/rule.mdis used to audit cookie headers.\n - Context: The network operation is a standard diagnostic tool for the skill's stated purpose and targets a placeholder domain.\n- [INDIRECT_PROMPT_INJECTION]: The skill audits external websites for privacy compliance, which involves processing potentially untrusted data from third-party domains.\n
- Ingestion points: The agent is instructed to review website resources, scripts, and server configurations from external sites as described in
SKILL.mdandreferences/rule.md.\n - Boundary markers: The instructions do not provide explicit delimiters or warnings to separate the agent's core instructions from data retrieved from external sources.\n
- Capability inventory: The skill utilizes
curlfor header inspection and guides the agent to perform comprehensive reviews of browser-side tracking behaviors.\n - Sanitization: There is no explicit mechanism defined for the sanitization or validation of the data ingested during the auditing process.
Audit Metadata