pyats-f5-platform
Warn
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands using python3 to run a pyATS script ($PYATS_MCP_SCRIPT). This involves the use of environment variables like $MCP_CALL and $PYATS_TESTBED_PATH to execute locally defined scripts.
- [DATA_EXFILTRATION]: The skill specifically lists endpoints and workflows for accessing highly sensitive cryptographic material, including SSL private keys (/mgmt/tm/sys/crypto/key and /mgmt/tm/file/ssl-key). While intended for security auditing, this provides a capability for sensitive data exposure.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from network devices.
- Ingestion points: API responses from F5 BIG-IP endpoints listed in SKILL.md (e.g., /mgmt/tm/sys/*).
- Boundary markers: Absent. The skill does not define delimiters or instructions to ignore embedded commands in device output.
- Capability inventory: Execution of scripts via python3 and environment variables as described in the 'How to Call' section.
- Sanitization: Absent. There is no evidence of input validation or sanitization of the data retrieved from the devices before processing.
Audit Metadata