Scan documents and file metadata for OPSEC leaks: geotags, author, GPS EXIF, unit identifiers.
Single tool with minimal schema and generic description. Input schema present but lacks parameter descriptions. Tool description is adequate (89 chars) but parameter 'target' has no description explaining expected format, path traversal risks, or directory vs file handling. No output schema documented. No error handling guidance. Naming is clear (verb_noun: opsecscan_scan) but the tool lacks the depth expected for production use.
Scan documents and file metadata for OPSEC leaks: geotags, author, GPS EXIF, unit identifiers.. Returns JSON findings.
Parameter 'target' lacks description. LLM cannot infer whether it accepts files, directories, or both; whether it resolves symlinks; or what happens on permission errors.
No output schema documented. LLM cannot predict the structure of returned JSON (fields, types, nesting). Baseline: 100% of A+ tools document return types.
No error handling guidance. If target is invalid, unreadable, or missing, the tool provides no recovery hints. LLM cannot self-correct.
Input schema lacks constraints. 'target' is a bare string with no minLength, maxLength, pattern, or enum. LLM may pass invalid paths, URLs, or special characters.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
Tool description does not clarify scope. Does it scan only the target file, or recursively scan directories? Does it follow symlinks? What file types does it analyze?