alterlab-ssci-reflexivity-gate

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes user-provided qualitative research claims and positionality statements to verify academic trustworthiness.
  • Ingestion points: Researcher claims, positionality statements, and warrants provided in the prompt context are passed as arguments to a local linter script.
  • Boundary markers: The skill instructions direct the agent to manage data using a structured YAML 'Design Passport' schema.
  • Capability inventory: The skill can execute the included local Python linter and update the YAML Design Passport file.
  • Sanitization: The linter script (scripts/trustworthiness_checklist.py) uses standard string membership checks to identify over-generalized language and does not interpret or execute the user input as code.
  • [COMMAND_EXECUTION]: Executes a local Python linter script to automate criteria validation.
  • Evidence: SKILL.md defines the use of uv run python scripts/trustworthiness_checklist.py.
  • Analysis: The script is static, included within the skill package, and utilizes only the Python standard library. This is a secure implementation of local logic for domain-specific verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 11:26 PM
Security Audit — agent-trust-hub — alterlab-ssci-reflexivity-gate