ss-inspect
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of logical instructions for a diagnostic workflow without any malicious functionality.
- [CREDENTIALS_UNSAFE]: The instructions demonstrate security awareness by explicitly instructing the agent not to include live secrets or credentials when referencing configuration values in the final report: "never paste live configuration values that might contain secrets into any report".
- [PROMPT_INJECTION]: The skill has an inherent attack surface as it is designed to ingest and process potentially untrusted data from system logs and error messages.
- Ingestion points: Phase 2 instructs gathering data from alerts, metrics, logs, traces, and code history.
- Boundary markers: Absent; the skill encourages reading and copying exact error text without specifying the use of delimiters or isolation.
- Capability inventory: The skill implies the use of tools for file reading (logs and code), network access (fetching metrics and traces), and subprocess execution (git commands).
- Sanitization: Partial; the skill warns against secret exposure but does not explicitly mention sanitizing content for embedded instructions.
Audit Metadata