cover-letter-skill

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill does not contain any executable code, scripts, or binary files. It relies entirely on natural language instructions and built-in agent tools (Read, Write, Structured Interaction).
  • [SAFE]: No hardcoded credentials, API keys, or sensitive file paths (like SSH keys or environment files) were identified.
  • [SAFE]: No external network operations (curl, wget, or API fetches) are performed. The skill only interacts with local files provided by the user or included in the skill's reference directory.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes untrusted user data (manuscript files or pasted text).
  • Ingestion points: Manuscript content is ingested via the Read tool or pasted text as defined in Step 1 of the Workflow in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or triple quotes) to isolate the untrusted paper content from the system instructions.
  • Capability inventory: The skill has the capability to write files to the local filesystem using the Write tool.
  • Sanitization: There is no explicit sanitization or filtering logic mentioned for the data extracted from user papers before it is included in the output letter.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 11:54 AM
Security Audit — agent-trust-hub — cover-letter-skill