skills/pudap/skills/puda-database/Gen Agent Trust Hub

puda-database

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes results from database queries executed via the puda db exec command. Content retrieved from the database could potentially contain instructions that influence the agent's behavior.
  • Ingestion points: Database query results returned by the puda CLI as described in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded in the query output.
  • Capability inventory: The skill allows execution of shell commands through the puda utility.
  • Sanitization: Absent. There is no mention of filtering or escaping the data retrieved from the database before the agent processes it.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands using the puda CLI tool to interact with the database.
  • Evidence: The skill instructs the agent to run puda db schema and puda db exec "<SQL>" to perform its primary tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:49 AM
Security Audit — agent-trust-hub — puda-database