informat@1.0.1
VERIFIED· install onlyPublisher claims: "Use when operating the 织信/Informat platform, including apps, tables, workflows, automations, scripts, APIs, dashboards, records, listeners, schedules, or platform-generated files." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 2026-11-10 and scored it 86/100 (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 deviationst+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
LOW
Rule modification attemptreferences/doc/markdown/informat.expression.md:150 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file
AST01**Rule 4: Operators must be inside `${}`**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Rule modification attemptreferences/doc/markdown/informat.expression.md:110 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file
AST01**Rule 1: `${}` must wrap a complete expression statement (most important)**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Rule modification attemptreferences/doc/markdown/informat.expression.md:156 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file
AST01**Rule 5: Only functions that exist in the documentation can be used; fabricating functions is prohibited**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.HIGH
Access to sensitive file pathsSKILL.md:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05Do not use `Read` on `/root/.informatclaw/config/skills/informat`; do not use `$INFORMAT_CONFIG_DIR`, `{baseDir}`, `/data/workspace/informat`, or guessed paths; do not write or rely on `scripts/.env`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathsscripts/call_informat.js:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05console.error("Failed to read optional .env file: " + envPath + ", " + e.message);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathsSKILL.md:86 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05…xplicitly pass `--threadId` as described above. Never write or rely on `scripts/.env`. > INFORMAT_AGENT_TOKEN can be obtained at: <informat host>/workbench/account…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.LOW
Rule modification attemptreferences/doc/markdown/informat.expression.md:144 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file
AST01**Rule 3: Raw values of list select fields should not be quoted**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Rule modification attemptreferences/doc/markdown/informat.expression.md:138 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file
AST01**Rule 2: Nesting `${}` inside `${}` is prohibited**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Authorization escalation languagereferences/system_app_get_web_url.json:5 · Authorization escalation language · informational: not an instruction file
AST01…ion": { "name": "_app_get_web_url", "description": "Get the website Web root access address of the current Informat application. The returned URL can be directly u…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.HIGH
Access to sensitive file pathsscripts/call_informat.js:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05// ---- Optionally load configuration from .env file ----Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathsscripts/call_informat.js:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05var envPath = nodePath.join(__dirname, ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Instructions loaded
≈15,430 tok
1 file · 288 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.