Skills/ClawHub/infinitycontext

infinitycontext@1.8.7

VERIFIED· install only

Publisher claims: "Use when a long agent session is about to hit its context limit, when a detail from an earlier turn must be recalled exactly, or when past sessions should stay searchable offline. Compresses context, archives conversation chunks into a local SQLite/FTS5 store with owner-only permissions and a bounded 30-day retention window, and retrieves exact details on demand. Ships explicitly opt-in maintenance tools that change local files: a retention cleanup that permanently deletes expired archive files (verified archive marker + filename allowlist + --confirm-destructive), an ingest-time retention purge with --purge-only, an INFINITY_CONTEXT_NO_ARCHIVE=1 off switch, and an in-place redaction helper that rewrites a file only inside a declared --allow-dir. Works out of the box on DeepSeek Harness (dsh) and OpenClaw; also runs on Claude Code, Cursor, Dify, Ollama and any Agent Skills host." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher pondsi · publishing for 74 daysInstalls 725Last detonated 7d ago
$clawhub install infinitycontext
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:172 · File type combined with upload action — agent may exfiltrate local data files- **Append is identity-checked, not prefix-matched** — `--append` only accepts a file whose **complete** name is `{safe_key}-YYYYMMDD-HHMMSS.db`, opens it **read-only first** and requires the exact `sFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:168 · File type combined with upload action — agent may exfiltrate local data files- **Fail-closed redaction** — before any text is stored, a regex redactor masks API keys, tokens, passwords, JWTs, private keys, connection strings, cookies, webhooks, phone numbers and emails. Rules Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandscripts/secure_fs.py:18 · File permission modification command — agent changes file ownership/permissionsso it never exists with wider permissions (no check-then-chmod race).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈6,220 tok
1 file · 16 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.