Intel Synthesis

WarnAudited by ClawScan on May 10, 2026.

Overview

The skill is mostly aligned with generating intelligence briefings, but it also tells the agent to use a configured email account to send briefing PDFs to fixed external Gmail recipients without a clear approval or credential boundary.

Only install or run this skill if you intend it to read the specified intelligence files, reuse prior briefings, generate PDFs locally, and potentially send those PDFs by email. Before use, disable or gate the email-dispatch step unless the recipients and sending account are exactly what you want.

Findings (6)

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.

What this means

The agent could send intelligence briefing PDFs from your email account to the listed recipients, exposing local/generated information and using your account identity.

Why it was flagged

The skill instructs use of a configured email account to send generated files to fixed external recipients, while the registry declares no primary credential, required environment variables, or account scope.

Skill content
Construct email with `himalaya` using the configured account. Attach: `[Date]_briefing_EN.pdf`, `[Date]_briefing_AR.pdf`. Recipients: `abdayi@gmail.com`, `mdurankaddatz@gmail.com`, `corebrain2026@gmail.com`.
Recommendation

Require explicit user approval before sending, make recipients configurable, declare the email credential/account requirement, and show a draft with attachments before dispatch.

What this means

A generated briefing could be transmitted externally as part of the normal workflow rather than just produced locally for review.

Why it was flagged

The delivery step gives the agent a high-impact external action—sending emails with attachments—without a stated confirmation gate or limit beyond hard-coded recipients.

Skill content
**Email Dispatch:**
  - Construct email with `himalaya` using the configured account.
  - Attach: `[Date]_briefing_EN.pdf`, `[Date]_briefing_AR.pdf`.
Recommendation

Add a mandatory review-and-confirm step before any email send, and default to saving drafts or local files unless the user explicitly asks to dispatch.

What this means

The skill may fail or behave differently depending on which local tools and templates are present.

Why it was flagged

The skill depends on local command-line tools and a local template, but the registry requirements say there are no required binaries and there is no install spec.

Skill content
use **MacTeX** ... `/Library/TeX/texbin/xelatex` ... Pandoc command: `pandoc [input.md] -o [output.pdf]` ... Construct email with `himalaya`
Recommendation

Declare required binaries and template paths in metadata, document expected versions, and avoid relying on undeclared local environment assumptions.

What this means

Installing or running the skill can cause local TeX/PDF tooling to execute and write files to the briefing output directory.

Why it was flagged

The skill tells the agent to invoke local PDF-generation commands. This is expected for the stated PDF delivery purpose, but it is still local command execution.

Skill content
Command: `/Library/TeX/texbin/xelatex -output-directory=/Volumes/Intel/NewsBriefs/ [filename].tex`
Recommendation

Review generated .tex files before compiling, keep TeX tooling updated, and run the skill only on trusted input directories.

What this means

If old briefing files are incorrect or tampered with, the agent may omit, reframe, or misclassify current stories.

Why it was flagged

The skill intentionally reuses a prior briefing as context for deduplication and update framing, so prior saved outputs can influence future briefings.

Skill content
**Persistence Check:** Read the most recent `[YYYY-MM-DD]_briefing_EN.md` from `/Volumes/Intel/NewsBriefs/`.
Recommendation

Keep the briefing archive trusted, review prior-context use, and consider requiring the agent to show which previous briefing was used.

What this means

Readers may trust the briefing more than warranted because source provenance is hidden from the delivered narrative.

Why it was flagged

The skill asks for an authoritative narrative while removing visible source tags, which makes the final briefing harder for recipients to verify.

Skill content
**No Citations:** Do not include source tags (e.g., `[Reuters]`) in the text. The narrative must flow seamlessly as an authoritative voice.
Recommendation

Include a source appendix, claim-source map, or internal citation record even if the main narrative remains polished.