compress-file
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill focuses on text analysis and file modification for the purpose of document compression.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided files as data, which is an inherent attack surface for indirect prompt injection. However, the logic is limited to structural manipulation and does not exhibit high-risk autonomous behaviors.
- Ingestion points: Reads user-supplied instruction files in Step 1.
- Boundary markers: Absent; the skill does not explicitly define delimiters to isolate target file content from the agent's instructions.
- Capability inventory: Invokes the
tighten-instructionskill and uses file editing tools to apply changes. - Sanitization: None specified; relies on the agent's internal safety filters.
Audit Metadata