swift-clean-names

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted Swift source code to perform renaming tasks.
  • Ingestion points: Untrusted Swift code is read from files or snippets via the Read and Glob tools (SKILL.md).
  • Boundary markers: The skill lacks explicit delimiters or specific instructions to the agent to disregard instructions potentially embedded within the code being analyzed.
  • Capability inventory: The skill is authorized to use Edit and Bash tools, allowing for potential misuse if the agent follows instructions hidden within the target code.
  • Sanitization: No input validation or filtering is performed on the content before the agent evaluates it for naming violations.
  • [PROMPT_INJECTION]: The skill directly interpolates user-provided $ARGUMENTS into its prompt block ('The user provided: $ARGUMENTS'), which could allow a malicious user to supply strings that attempt to override the skill's primary instructions or bypass safety constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:39 PM
Security Audit — agent-trust-hub — swift-clean-names