txt-copy
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Bash commands to utilize system clipboard utilities including pbcopy, xclip, and xsel. This execution is scoped to the primary purpose of the skill and does not attempt to gain unauthorized access.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses the capability to process arbitrary text content which may originate from untrusted external sources.
- Ingestion points: Text content provided by the user or generated by the agent is written to a temporary file as described in SKILL.md.
- Boundary markers: The workflow uses single-quoted heredocs (<< 'EOF') which serves as a boundary to prevent the shell from expanding variables or executing commands found within the text being copied.
- Capability inventory: The skill uses subprocess execution (Bash), file system writes and deletions within /tmp, and interaction with the system clipboard tools.
- Sanitization: Shell-level command injection is prevented by the instruction to use the single-quoted EOF marker, ensuring the content is handled strictly as literal data.
Audit Metadata