TLDR Prompt
AdvisoryAudited by Static analysis on May 12, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
NoteHigh Confidence
ASI02: Tool Misuse and ExploitationWhat this means
When invoked, the agent may inspect selected workspace files or retrieve web pages to produce the TLDR summary.
Why it was flagged
The skill directs the agent to use file-reading and fetch tools. This is expected for creating summaries, and the visible instructions bound usage to user-provided files/URLs or relevant Copilot/MCP documentation.
Skill content
"If one or more files are passed without `#file`, you MUST apply the file reading tool"; "If one or more URLs are passed without `#fetch`, you MUST apply the fetch tool"
Recommendation
Provide explicit files or URLs when possible, and avoid pointing the skill at sensitive local files unless you want them summarized in the current chat.