paper-positioning-planner

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external content while possessing broad system capabilities.
  • Ingestion points: The skill reads user-provided project data, including paper drafts, abstracts, and literature maps in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or safety markers to isolate processed data from the agent's command logic.
  • Capability inventory: The skill is allowed a wide range of powerful tools such as Bash, Read, Write, Edit, and WebFetch, which could be misused if malicious instructions are present in analyzed documents.
  • Sanitization: There is no evidence of input validation or content filtering before the agent processes user-provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 09:31 AM
Security Audit — agent-trust-hub — paper-positioning-planner