temporal-continuity

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill specifies a data ingestion surface by instructing the agent to read an external documentation file. \n- Ingestion points: ../../references/TEMPORAL_CONTINUITY.md (referenced in SKILL.md). \n- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded prompts within the referenced file. \n- Capability inventory: None; no specialized tools, subprocess calls, or network operations are defined within this skill file. \n- Sanitization: Absent; the content is intended to be read and followed as a procedural guide without filtering. \n- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The relative path points to a standard documentation directory within a typical project structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:42 AM