cve-triage
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed around executing various shell commands via the
infynon pkgCLI, including scanning for vulnerabilities, performing automated fixes, and auditing dependency trees. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It instructs the agent to ingest and parse JSON output from
infynon pkg scanand directly execute remediation steps based on thefix_cmdfield provided in that data. - Ingestion points: The agent reads and processes output from the
infynon pkg scan --jsoncommand. - Boundary markers: There are no explicit markers or instructions to treat the ingested JSON data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The agent has shell access via the
infynon pkgcommand, which allows for package installation, environment modification, and system auditing. - Sanitization: The instructions do not specify any validation or sanitization of the
fix_cmdorpackagefields before interpolation into execution commands.
Audit Metadata