triage-expert
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several shell commands (e.g.,
uname,node,npm,ps,netstat,df,free,grep) to conduct environment audits and monitor system resources. These operations are directly relevant to the skill's stated purpose of providing technical triage and diagnosis. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted data such as error messages, log traces, and project source code, creating a surface for injection attacks.
- Ingestion points: Collects project configuration, error logs, and execution traces from the filesystem and command outputs.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded directives when aggregating context for the final handoff package.
- Capability inventory: Has the ability to execute shell commands, read system state, and create/delete temporary diagnostic scripts.
- Sanitization: The instructions do not include mechanisms for sanitizing or validating external content before it is processed or reported.
Audit Metadata