HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
SeanHeelan
anamnesis-release
JavaScript2026–2026
SeanHeelan / anamnesis-release

anamnesis-release

Automatic Exploit Generation with LLMs

2Distinct people
2Mentions
0Explicit recommenders
641GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Automatic Exploit Generation with LLMs

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour2 dated mentions

Observed mentions: 2026-01-20 08:10:04 UTC to 2026-01-20 22:23:38 UTC.

012026-01-20 08:00:00 UTC to 2026-01-20 09:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJan 20, 08:002026-01-20 09:00:00 UTC to 2026-01-20 10:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 10:00:00 UTC to 2026-01-20 11:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 11:00:00 UTC to 2026-01-20 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 12:00:00 UTC to 2026-01-20 13:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 13:00:00 UTC to 2026-01-20 14:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 14:00:00 UTC to 2026-01-20 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 15:00:00 UTC to 2026-01-20 16:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsJan 20, 15:002026-01-20 16:00:00 UTC to 2026-01-20 17:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 17:00:00 UTC to 2026-01-20 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 18:00:00 UTC to 2026-01-20 19:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 19:00:00 UTC to 2026-01-20 20:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 20:00:00 UTC to 2026-01-20 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 21:00:00 UTC to 2026-01-20 22:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-01-20 22:00:00 UTC to 2026-01-20 23:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJan 20, 22:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Jan 20, 08:002026-01-20 08:00:00 UTC2026-01-20 09:00:00 UTC101
Jan 20, 09:002026-01-20 09:00:00 UTC2026-01-20 10:00:00 UTC000
Jan 20, 10:002026-01-20 10:00:00 UTC2026-01-20 11:00:00 UTC000
Jan 20, 11:002026-01-20 11:00:00 UTC2026-01-20 12:00:00 UTC000
Jan 20, 12:002026-01-20 12:00:00 UTC2026-01-20 13:00:00 UTC000
Jan 20, 13:002026-01-20 13:00:00 UTC2026-01-20 14:00:00 UTC000
Jan 20, 14:002026-01-20 14:00:00 UTC2026-01-20 15:00:00 UTC000
Jan 20, 15:002026-01-20 15:00:00 UTC2026-01-20 16:00:00 UTC000
Jan 20, 16:002026-01-20 16:00:00 UTC2026-01-20 17:00:00 UTC000
Jan 20, 17:002026-01-20 17:00:00 UTC2026-01-20 18:00:00 UTC000
Jan 20, 18:002026-01-20 18:00:00 UTC2026-01-20 19:00:00 UTC000
Jan 20, 19:002026-01-20 19:00:00 UTC2026-01-20 20:00:00 UTC000
Jan 20, 20:002026-01-20 20:00:00 UTC2026-01-20 21:00:00 UTC000
Jan 20, 21:002026-01-20 21:00:00 UTC2026-01-20 22:00:00 UTC000
Jan 20, 22:002026-01-20 22:00:00 UTC2026-01-20 23:00:00 UTC101

What Hacker News says

2 sources
I'm really confused by the sandbox part. The description kind of mentions it and the limited system syscall, but then just pivots to talking about the exit handlers. It may be just unclear writing, but now I'm suspicious of the whole thing. https://github.com/SeanHeelan/anamnesis-release/?tab=readme-... feels like the author lost track. If forking is blocked, the exit handler can't do it either. If it's some variant of execve, the sandbox is preserved so we didn't gain much. Edit: ok, I get it! Missed the "Goal: write exactly "PWNED" to /tmp/pwned". Which makes the sandbox part way less interesting as implemented. It's just saying you can't shell out to do it, but there's no sandbox breakout at any point in the exploit.
In The coming industrialisation of exploit generation with LLMs

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.