target-journal-matcher
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research abstracts as input to its scoring logic, creating a surface for indirect prompt injection.
- Ingestion points: The
scripts/main.pyscript ingests untrusted text via the--abstractcommand-line argument. - Boundary markers: None; the abstract text is processed directly as a string.
- Capability inventory: The skill only performs text analysis and prints results to the console. It has no capabilities for file writing, network operations, or subprocess execution.
- Sanitization: The script uses regular expression keyword matching and keyword frequency analysis (
Counter) to characterize the input, which naturally filters out non-content words but does not explicitly sanitize for malicious instructions.
Audit Metadata