tw-research-abstract-optimizer

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted user input.
  • Ingestion points: The skill ingests user abstracts in SKILL.md at Step 4 via the placeholder variable.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the model to ignore any potential directives embedded within the academic abstract text.
  • Capability inventory: The skill's frontmatter configuration includes 'Bash', 'Read', and 'Write' tools, which could be leveraged if a prompt injection was successfully executed.
  • Sanitization: No input validation or sanitization logic is present to filter malicious instructions from the processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 11:02 AM
Security Audit — agent-trust-hub — tw-research-abstract-optimizer