swift-clean-errors

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via the $ARGUMENTS variable and the content of files retrieved using the Read tool. It lacks boundary markers to separate data from instructions, which may allow malicious content within the analyzed source code to influence agent behavior.
  • Ingestion points: User-provided arguments in SKILL.md and Swift source code content processed by the Read tool.
  • Boundary markers: Absent. The skill does not use delimiters or explicit instructions to treat code content as data only.
  • Capability inventory: The skill is configured with Bash, Edit, Read, Glob, and Grep capabilities, enabling file modification and shell command execution.
  • Sanitization: Absent. There is no evidence of input validation or escaping for external content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The instructions direct the agent to automatically apply code fixes using the Edit tool based on the results of the audit. This creates a direct path for the agent to modify the local filesystem based on its interpretation of the code, which could be exploited if the audit process is subverted by malicious input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:40 PM
Security Audit — agent-trust-hub — swift-clean-errors