paper-review

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests and processes untrusted external data from a user-provided paper directory, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: The skill reads various artifact types including prose (.tex), bibliographies (.bib), and analysis scripts (.py, .R, .sh, .do, .jl) as described in SKILL.md Steps 1 through 9.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives when the agent reads these external files.
  • Capability inventory: The skill is capable of writing audit reports to the local filesystem and invoking the compile-latex tool.
  • Sanitization: There is no explicit requirement for the agent to sanitize or filter the ingested content before it is processed or included in the audit report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 02:29 PM
Security Audit — agent-trust-hub — paper-review