Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/forecasting-time-series-data/Gen Agent Trust Hub

forecasting-time-series-data

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and analyze external time-series data (e.g., CSV files).
  • Ingestion points: Processes historical time-series data from user-provided or local files as described in SKILL.md and assets/README.md.
  • Boundary markers: Absent. The instructions do not include delimiters or specific guidance for the agent to ignore potentially malicious instructions embedded within the data files.
  • Capability inventory: The skill is granted high-privilege tools including Bash(cmd:*), Write, and Edit in SKILL.md, which could be exploited if malicious instructions are successfully injected via a data file.
  • Sanitization: Absent. No evidence of input validation or escaping for the data being processed.
  • [NO_CODE]: Several core script files required for the skill's primary functionality are missing.
  • Evidence: The file scripts/README.md explicitly lists forecast.py, evaluate.py, and preprocess.py as bundled resources, but these files are not present in the skill directory.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 10:43 AM
Security Audit — agent-trust-hub — forecasting-time-series-data