@vib795/agent-memory 0.5.1 → 0.5.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +27 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -207,6 +207,33 @@ name on it. What this is not: it is not encryption, access control, or a DLP pro
|
|
|
207
207
|
It is one command that refuses to hand over identifiers, and it says exactly what it
|
|
208
208
|
checked.
|
|
209
209
|
|
|
210
|
+
### Independently scanned
|
|
211
|
+
|
|
212
|
+
Public supply-chain scanners index every package published to npm, so this one is
|
|
213
|
+
reviewed by people who owe it nothing. That is worth more than a clean claim from its
|
|
214
|
+
author.
|
|
215
|
+
|
|
216
|
+
[LPM Firewall](https://firewall.lpm.dev/npm/@vib795/agent-memory) currently reports
|
|
217
|
+
**Passed — safe to install**, with no policy match and no flagged code. Its reading of
|
|
218
|
+
the artefact — signed, provenance attached, zero dependencies, no install hooks — is a
|
|
219
|
+
third-party check on what this README says about itself. Four low-signal patterns
|
|
220
|
+
remain, and they are descriptive rather than policy: environment variables, scripts
|
|
221
|
+
present, filesystem, high-entropy strings. That is what a CLI which reads
|
|
222
|
+
`AGENT_MEMORY_HOME` and writes files in your home directory looks like from outside.
|
|
223
|
+
|
|
224
|
+
**It did not start there.** Version 0.3.1 was flagged **Critical — AI Agent Control
|
|
225
|
+
Hijack**, because `postinstall` wrote skill files into `~/.claude`, `~/.codex` and your
|
|
226
|
+
editor's prompt folder. The finding was correct. An install script that grants an AI
|
|
227
|
+
agent new instructions without the user asking is indistinguishable from an attack
|
|
228
|
+
that does exactly that, and good intent is not observable to a scanner. The hook was
|
|
229
|
+
removed in 0.4.0 rather than argued with, which is why `agent-memory setup` is a
|
|
230
|
+
command you type.
|
|
231
|
+
|
|
232
|
+
The 0.3.1 report is still public and still says Critical. Old version pages do not
|
|
233
|
+
come down, and they should not: a supply-chain record that could be edited after the
|
|
234
|
+
fact would be worth nothing. What a project can offer is the next version and the
|
|
235
|
+
reason for it.
|
|
236
|
+
|
|
210
237
|
## Engagements
|
|
211
238
|
|
|
212
239
|
If you work for more than one client on one machine, knowledge from one of them is
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@vib795/agent-memory",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.2",
|
|
4
4
|
"description": "Durable cross-repo knowledge graph for GitHub Copilot and Claude Code. Markdown source of truth, disposable SQLite index, zero runtime dependencies.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"github-copilot",
|