add-entity

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates arbitrary user input into code generation tasks.
  • Ingestion points: User-supplied data enters the context via the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: The skill lacks delimiters or explicit instructions to treat the interpolated input strictly as data, which may allow malicious payloads to influence agent behavior during code generation.
  • Capability inventory: The skill has the capability to read and write to sensitive core files, such as packages/server/api/src/app/database/database-connection.ts and postgres-connection.ts, and can execute local shell commands via npm run lint-dev.
  • Sanitization: There is no evidence of input validation, sanitization, or escaping of the user-provided arguments before they are written into the codebase.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell command (npm run lint-dev) to verify the integrity and formatting of the newly created files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:21 PM
Security Audit — agent-trust-hub — add-entity