Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local conversation-summary tool whose file access and output behavior match its stated purpose.
Install only if you are comfortable letting the tool process conversation transcripts you provide. Prefer explicit invocation for compression and avoid feeding sensitive chat histories unless the resulting Markdown summary is acceptable to store or share locally.
The skill advertises executable behavior through its usage instructions and metadata but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an authorization ambiguity where a host may expose file read/write capabilities more broadly than intended, which is especially relevant here because the skill processes conversation files and writes compressed output.
The activation guidance includes broad, everyday phrases like "continue," "where were we," and similar variants that can match normal conversation rather than an intentional request to invoke this skill. This can cause accidental triggering in unrelated contexts, leading to unintended summarization of conversation history and possible exposure or transformation of sensitive context.
No suspicious patterns detected.
