oh-my-ai/reading-synthesis
Produces a thirteen-part rigorous synthesis of a reading or talk—structure, insights, critique, framework rebuild, actions, and a compressed executive summary—for semi-technical audiences.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The SKILL.md explicitly requires using WebSearch/WebFetch to find and ingest comparands when the user names none (see "Uses: ... WebSearch or WebFetch" and Non‑negotiable #6 / Process #4), so the agent will fetch and interpret open, third‑party web content that can influence its analysis and actions.
Where we found it
arbitrary web content via WebSearch/WebFetch
content-type · 3 sites
The SKILL.md explicitly requires the agent to use WebSearch or WebFetch to find and ingest comparands when the user provides none (Non-negotiable #6 and Process #4), causing the agent to fetch and act on arbitrary third-party web content.
SKILL.md
3
Uses: Read (and related file tools) for attached sources; WebSearch or WebFetch when comparands are missing or context is thin.
SKILL.md
20
If the user names none, run **WebSearch** (or WebFetch on solid results) to propose defensible comparands.
SKILL.md
29
Research comparands if needed for section 5 — short, targeted queries; prefer stable, citable names and works.
- Audited
- Security analysis