signal-compress
Warn
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a PowerShell script (
scripts/signal-compress.ps1) with the-ExecutionPolicy Bypassflag. This flag is used to circumvent security restrictions that would normally prevent the execution of scripts on the host system. - [PROMPT_INJECTION]: The skill ingests and processes untrusted data from project documentation and memory files, exposing a surface for indirect prompt injection.
- Ingestion points: Documentation files like
GEMINI.md,CLAUDE.md, andAGENTS.mdprovided by the user. - Boundary markers: Absent; the skill does not use specific delimiters or instructions to prevent the agent from following commands embedded in the processed files.
- Capability inventory: The skill has access to shell command execution through PowerShell and the ability to read and overwrite local files.
- Sanitization: There is no evidence of sanitization or content validation for the files being compressed.
Audit Metadata