skills/lu1sdv/skillsmd/ssrf-testing/Gen Agent Trust Hub

ssrf-testing

Fail

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Automated bash scripts provided in SKILL.md and references/payloads.md use curl in loops to perform network scanning and parameter probing on target environments.
  • [DATA_EXFILTRATION]: The skill includes payloads and instructions to retrieve sensitive local files (e.g., /etc/passwd) and cloud metadata (AWS/GCP/Azure IAM credentials) and transmit them to external Out-of-Band (OOB) servers like oast.fun.
  • [EXTERNAL_DOWNLOADS]: The SKILL.md file recommends downloading and installing tools from untrusted GitHub repositories: swisskyrepo/SSRFmap and tarunkant/Gopherus, which are not part of the trusted vendor list.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by ingesting untrusted data from user-supplied URLs and remote application responses without boundary markers. Ingestion points: user-supplied parameters in SKILL.md. Boundary markers: absent. Capability inventory: subprocess calls to curl in loops. Sanitization: absent in provided test scripts.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 7, 2026, 07:18 PM