swift-concurrency-expert
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow for analyzing and fixing code issues creates a vulnerability to indirect prompt injection from untrusted data.\n
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to "Capture the exact compiler diagnostics and the offending symbol(s)" from the user, which are external inputs.\n - Boundary markers: The instructions lack defined delimiters or specific isolation prompts to separate user-provided compiler output from the agent's core instructions.\n
- Capability inventory: As a remediation tool, the agent likely has access to file-system tools (such as
read_fileandwrite_file) to analyze and modify project source code.\n - Sanitization: There is no evidence of validation or sanitization of the incoming diagnostic text before it is used to guide the agent's remediation tasks.
Audit Metadata