cflx-run
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard Git commands and a domain-specific CLI tool
cflx runto manage the development lifecycle. - [EXTERNAL_DOWNLOADS]: The skill performs repository synchronization using
git pullandgit fetchfrom configured remote repositories. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it reads and processes data from
openspec/changes/, which represents a potential injection surface if those files contain instructions intended to influence the agent's behavior. - Ingestion points: Specification files located in
openspec/changes/(SKILL.md). - Boundary markers: No explicit delimiters or instructions are used to separate data from instructions within the ingested files.
- Capability inventory: The agent can execute the
cflxtool and variousgitcommands based on the workflow state (SKILL.md). - Sanitization: The skill does not implement sanitization or validation of the content within the change specification files before proceeding with orchestration.
Audit Metadata