compress
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python modules and the
claudeCLI tool usingsubprocess.runto perform its core file processing and compression tasks. This behavior is consistent with the skill's stated purpose as a utility for the Claude Code environment. - [PROMPT_INJECTION]: The skill processes the content of user-specified files which are then used as part of a prompt to the language model, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill reads file content into memory within
scripts/compress.pyviafilepath.read_text(). - Boundary markers: The prompts include clear separators such as
TEXT:,ORIGINAL:, andCOMPRESSED:to distinguish instructions from user-provided data. - Capability inventory: The skill can read/write local files and execute shell commands through the CLI.
- Sanitization: No specific filtering or sanitization is performed on the ingested file content before it is interpolated into the model prompt.
Audit Metadata