alterlab-ssci-reflexivity-gate
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script,
scripts/trustworthiness_checklist.py, using theBashtool (viauv run python). This execution is restricted to the skill's own distributed code and is used to automate the auditing of qualitative research criteria. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research claims through its checklist script to detect over-generalization. This involves ingesting untrusted text into a command-line argument. The risk is mitigated by the script's limited functionality, which only performs keyword matching against a static list of terms (e.g., 'everywhere', 'universally') and does not execute the input as code.
Audit Metadata