israeli-tabu-extract-decoder
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and reference materials. It does not include any scripts, binaries, or automated tools, and explicitly states it performs no network calls in the SKILL.md frontmatter.
- [PROMPT_INJECTION]: Instructions regarding response formatting—such as framing findings as questions rather than legal verdicts—are designed for safety and regulatory compliance (avoiding unauthorized legal advice). A static detector flag for 'concealment' is a false positive triggered by these safety constraints, which actually promote transparent communication of sequence-based risks to the user by explicitly directing the agent to warn against transferring funds when certain encumbrances are found.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user-supplied text (ingestion point: pasted land registry extracts in SKILL.md), it has zero exploitable capabilities. The capability inventory shows no subprocess calls, network operations, or file-write capabilities across any of the files, which prevents the execution of any malicious instructions that could theoretically be embedded in the processed data.
- [EXTERNAL_DOWNLOADS]: The skill references authoritative legal sources on WikiSource (he.wikisource.org), which is a well-known and trusted service. No untrusted external resources are fetched or executed.
Audit Metadata