Skills
Navigate
skills/zju-real/easel/skill-data-tracker/Gen Agent Trust Hub

skill-data-tracker

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/track.py for recording snapshots and analyzing growth trends. This provides a deterministic execution environment for statistical calculations.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted external data such as social media metrics and post titles. (1) Ingestion point: SKILL.md defines input fields for platform metrics. (2) Boundary markers: Absent in prompt instructions. (3) Capability inventory: Subprocess execution of scripts/track.py and file writing to the outputs/ directory. (4) Sanitization: Present; scripts/track.py uses the _safe_segment function with regex to prevent path traversal in profile and platform names.
  • [SAFE]: The skill uses atomic write operations and maintains data isolation between profiles. No network requests, obfuscation, or persistence mechanisms were detected in the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 04:22 AM