000-TnR-Absolute-Rigor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt mandates exhaustive ingestion of local code/logs/configs and the inclusion of full, auditable evidence inline in a single session file (no external artifacts or redaction rules), which effectively forces the agent to read and potentially reproduce verbatim sensitive values (API keys, tokens, passwords) from those sources.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)