almerge
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download thealignfirstpackage from the NPM registry. This package belongs to the skill's author (Paleo) as indicated in the metadata and repository fields. - [REMOTE_CODE_EXECUTION]: The instruction to run
npx -y alignfirst guide mergeresults in the execution of remote code fetched from the NPM registry at runtime. As the package is a known resource from the vendor, this is standard tool behavior. - [COMMAND_EXECUTION]: The skill executes a shell command to retrieve instructions, which is a standard operation for developer-oriented skills.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to follow instructions contained within the output of the
alignfirstcommand. This establishes a surface where external content could influence the agent's logic. - Ingestion points: Output of
npx -y alignfirst guide mergein SKILL.md. - Boundary markers: None.
- Capability inventory: The agent is tasked with following the protocol guide and work file rules provided by the command.
- Sanitization: None.
Audit Metadata