skills/bfly123/claude_code_bridge/tp/Gen Agent Trust Hub

tp

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script at ~/.claude/skills/tr/scripts/autoloop.sh by passing a command to the /file-op tool to initialize an execution loop.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its data ingestion and execution capabilities.
  • Ingestion points: Untrusted data is ingested through the $ARGUMENTS variable and external web content retrieved via WebSearch and WebFetch operations in the flow.md execution logic.
  • Boundary markers: The skill does not define clear delimiters or instructions to treat web-fetched content as data rather than instructions, which could allow maliciously crafted web content to influence the planning process.
  • Capability inventory: The skill has the capability to execute shell commands and write files via the /file-op tool, and perform network requests via WebSearch/WebFetch.
  • Sanitization: No sanitization, validation, or filtering of the content retrieved from web sources is performed before it is integrated into the task plan and subsequent execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 06:11 AM