identity-snapshot
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No critical or high-severity security issues were detected. The skill performs routine file management and summarization tasks.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its data ingestion patterns.
- Ingestion points: Reads multiple Markdown and JSONL files (e.g., Session_Learnings/*.md, Tasks.md, user-profile.yaml) to extract behavioral patterns and personal identity information.
- Boundary markers: The skill does not provide delimiters or instructions to isolate source data from instructions, allowing potential directives in the source files to influence the synthesis.
- Capability inventory: The skill's actions are restricted to reading internal project data and writing the System/identity-model.md output file. No network access or external command execution tools are utilized.
- Sanitization: The skill does not implement validation or sanitization of the processed content.
Audit Metadata