Markdown Is the New Executable: Attackers Drop Agent Instructions into Downloads
Comments on “Markdown Is the New Executable: Attackers Drop Agent Instructions into Downloads”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
A security write-up from Forever Security describes how a malicious AGENTS.md file, silently dropped into a user's ~/Downloads folder by a website, can be executed by AI coding agents like OpenAI Codex and Claude Code, which automatically obey instructions files in the folders they open.
Why it ranked
No. 29 of 124 with a score of 0.66. The panel rated it highest on reader interest (0.89) and new information (0.88), lowest on substantiated (0.69). Overclaim counted against it (0.59). The judges disagreed most on promotional (spread 0.59), so the story is marked contested.
Every answer behind this is in the table under Score.
Score
0.66total under rubric v2.2Contestedjudges differ by 0.59 on promotional, 0.46 on overclaim
- Significance0.72
- Reader interest0.89
- Audience breadth0.75
- Practical relevance0.85
- Substantiated0.69
- Technical depth0.86
- New information0.88
- Counts against: Promotional0.43
- Counts against: Overclaim0.59
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.76 | 0.62 | 0.78 | 0.72 | 0.16 | +0.24 | +0.173 |
| Reader interest | 0.88 | 0.88 | 0.90 | 0.89 | 0.02 | +0.26 | +0.231 |
| Audience breadth | 0.82 | 0.70 | 0.72 | 0.75 | 0.12 | +0.13 | +0.097 |
| Practical relevance | 0.89 | 0.80 | 0.86 | 0.85 | 0.09 | +0.22 | +0.187 |
| Substantiated | 0.85 | 0.60 | 0.62 | 0.69 | 0.25 | +0.05 | +0.035 |
| Technical depth | 0.98 | 0.78 | 0.82 | 0.86 | 0.20 | +0.05 | +0.043 |
| New information | 0.88 | 0.85 | 0.90 | 0.88 | 0.05 | +0.05 | +0.044 |
| Promotional | 0.13 | 0.45 | 0.72 | 0.43 | 0.59 , above the contested threshold | −0.19 | −0.082 |
| Overclaim | 0.51 | 0.40 | 0.86 | 0.59 | 0.46 , above the contested threshold | −0.11 | −0.065 |
| Sum of contributions | +0.661 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.661 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-10-27/29/"><img src="https://rubric.hrih.si/badge/2026-10-27/29.svg" alt="Ranked #29 on Rubric, 27 Oct 2026" width="245" height="28"></a>Also covered by
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 27 Oct 2026, 05:46 UTC. It played no part in the ranking.