extraction-form

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill performs routine data extraction and formatting tasks for systematic reviews. It interacts only with project-specific files such as screening logs and protocols. No unauthorized file access or network activity was detected.
  • [NO_CODE]: The skill is composed of instructions in markdown format and does not include any scripts, dependencies, or compiled code.
  • [PROMPT_INJECTION]: The skill ingests data from external files (papers/screening_log.csv, output/PROTOCOL.md, papers/paper_notes.jsonl) which represents a surface for indirect prompt injection. However, the risk is negligible given the lack of dangerous capabilities like shell execution or internet access. * Ingestion points: papers/screening_log.csv, output/PROTOCOL.md, papers/paper_notes.jsonl. * Boundary markers: Absent. * Capability inventory: Reading and writing local files within the project. * Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:47 AM