bug-prospector

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behaviors such as data exfiltration, credential harvesting, or unauthorized privilege escalation were detected. The skill uses restricted Bash commands solely for Git status checks and terminal layout configuration.- [PROMPT_INJECTION]: The skill implements a surface for indirect prompt injection by design, as its primary function is to read and analyze untrusted external source code files.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to read the full contents of Swift files (**/*.swift) from the local workspace for analysis.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in the analyzed data are provided.
  • Capability inventory: The skill possesses Bash (restricted to Git/tput), Write (to report files), and AskUserQuestion capabilities.
  • Sanitization: The skill does not perform sanitization, escaping, or structural validation on the ingested code before processing it in the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:17 PM
Security Audit — agent-trust-hub — bug-prospector