title-generator

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured multi-step process for title generation that relies on local reference data and explicit pattern matching. It does not require external network access or execute arbitrary system commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Markdown files, which represents a potential surface for indirect prompt injection.
  • Ingestion points: Article content read from filesystem paths provided by the user (Step 1 in SKILL.md).
  • Boundary markers: Absent; the prompt does not specify delimiters to separate untrusted content from instructions.
  • Capability inventory: The agent utilizes file-reading capabilities to extract information from the documents.
  • Sanitization: None; the skill directly extracts technical keywords and metadata from the processed text. However, since the risk is inherent to the primary function of a text analysis tool and no sensitive actions are performed on the data, the severity is considered minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:19 AM
Security Audit — agent-trust-hub — title-generator