ise-posture-audit
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands using
python3andnodebased on environment variables ($MCP_CALL,$ISE_MCP_SCRIPT,$MARKMAP_MCP_SCRIPT). These commands are used to interact with Cisco ISE APIs and generate visualization artifacts. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it retrieves and processes configuration data from an external source (Cisco ISE).
- Ingestion points: Untrusted data enters the agent context through the output of tools like
network_access_policy_set,network_access_authorization_rules, andendpoints(referenced inSKILL.md). - Boundary markers: The instructions do not define delimiters or provide specific warnings to the agent to ignore instructions embedded within the audited network data.
- Capability inventory: The skill has access to shell execution (
python3,node) and credential-handling environment variables, which could be leveraged if an injection is successful. - Sanitization: There is no evidence of sanitization, escaping, or schema validation for the data retrieved from the ISE environment before the agent evaluates it.
Audit Metadata