convert
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executeasciinemaconversion and management commands. This is consistent with the skill's primary purpose of processing terminal session recordings. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (terminal recordings) and provides an
--analyzeflag to pass the resulting text to an agent. This creates a surface for indirect prompt injection if the recording contains malicious instructions designed to be interpreted by the AI during analysis. - Ingestion points: Reads
.castfiles provided by the user or found in~/asciinemalogs(SKILL.md). - Boundary markers: None explicitly defined in the conversion logic; the output is raw text.
- Capability inventory:
Bashtool for command execution andWritetool for file creation (SKILL.md). - Sanitization: No specific sanitization or filtering of terminal escape sequences or embedded text is mentioned beyond the standard
asciinemaconversion process.
Audit Metadata