analyzing-certificate-transparency-for-phishing
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing untrusted data from public Certificate Transparency logs and incorporating it into terminal output and generated markdown reports.
- Ingestion points: External data enters the context through crt.sh API responses in
query_crt_sh(Step 1) and real-time Certstream WebSocket messages instart_monitoring(Step 2). - Boundary markers: There are no explicit delimiters or instructions to the agent to disregard potentially malicious commands or markdown within the certificate fields.
- Capability inventory: The skill has file-write capabilities in Step 4, where it creates
ct_report_{domain}.mdon the local filesystem. - Sanitization: The skill does not sanitize certificate metadata (e.g.,
common_name,issuer_name) before including it in the report, allowing a malicious certificate owner to potentially inject markdown or instructions intended to influence the agent or the user.
Audit Metadata