developer-growth-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to read
~/.claude/history.jsonlto identify work patterns. This file contains private interaction history and project details. This access is local and required for the stated purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes historical chat logs which could contain content from external sources, acting as an ingestion point for indirect prompt injection.
- Ingestion points: The
~/.claude/history.jsonlfile. - Boundary markers: There are no specific instructions to use delimiters or ignore instructions embedded within the historical data.
- Capability inventory: The agent analyzes the file content to generate a growth report.
- Sanitization: No sanitization steps are provided for the input history data.
Audit Metadata