speak-common-errors
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze error messages from API logs and console output (references/implementation-guide.md). This creates a vulnerability surface where an attacker could potentially embed malicious instructions within an error message or log entry. If the agent processes these logs without sanitization or boundary markers, it might interpret the embedded instructions as authoritative. Evidence: Ingestion points in implementation-guide.md (Step 1); Capabilities include Bash, Read, Write, and Edit; No sanitization or boundary markers are defined for log ingestion.
Audit Metadata