Jiffy Intel — Threat intelligence for AI artifacts

Summary

MCP server saves boto session credentials (including short-lived session tokens) in a file under /tmp without restricting permissions. Other processes on the same host can read the file and hijack the session.

Severity & confidence

Severity

High

Credible abuse path with meaningful impact on confidentiality, integrity, or availability. Remediate on a short timeline; do not wait for the next sprint cycle.

Confidence

Confirmed

Observed directly by Jiffy scanners or validated by multiple independent sources. Indicators are reliable enough to drive automated action.

Indicators

Observed patterns and artifacts associated with this entry. Each indicator can be copied into your detection stack or SIEM.

(?i)open\s*\(.{0,80}/tmp/[^"']*(?:aws|boto|session)

Detection rule

A YARA-style pseudo-rule auto-generated from the indicators above. Useful as a starting point — adapt the syntax for your target detection platform.

YARA-style pseudo-rule

rule jiffy_ti_2026_000045
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $command_pattern_0 = "(?i)open\\s*\\(.{0,80}/tmp/[^\"']*(?:aws|boto|session)"
    condition:
        $command_pattern_0
}

Auto-generated from the indicators above. Adapt syntax for your detection stack before deploying.

Affected tools

Tool	Versions	Status
MCP servers (Python/boto)	`*`	vulnerable

Example artifacts

Sanitized examples of artifacts Jiffy has observed exhibiting this pattern. Publisher handles are redacted; version ranges and status reflect the most recent scan.

aws-ops-mcpMCP server
Under review
Source
MCP Registry
Versions
0.1.0
First observed
Mar 11, 2026
cloud-inspector-mcpMCP server
Quarantined
Source
Community registry
First observed
Mar 15, 2026

How to remediate

01Store credentials in-memory only or in a secured keyring.
02Reject MCP servers that write credentials to /tmp.

Timeline & sources

Timeline

First observedMar 11, 20261 month ago
Last updatedApr 24, 2026today
PublishedMar 25, 202623 days ago

Sources

scanner

References

attack.mitre.org

MITRE ATT&CK T1555 — Credentials from Password Stores

https://attack.mitre.org/techniques/T1555/

genai.owasp.orgOWASP

OWASP LLM-02: Sensitive Information Disclosure (2026)

https://genai.owasp.org/llmrisk/llm-02-2026/

Related intel

Other entries of type Credential Exfil, or the most recent published entries if no same-type matches exist.

Credential ExfilHigh

.cursorrules fetches remote rule that encodes "submit secrets" logic

.cursorrules with `extends: <url>` resolves to a remote rule set whose content includes directives to read repo-local .env and post-process before any commit. A separation between policy declaration (local) and policy content (remote) hides the exfiltration.

Jiffy IntelApr 27

Credential ExfilHigh

Custom GPT Action logs full request bodies including Authorization headers

Action backend that logs every inbound request, including the OAuth Authorization header forwarded by the GPT. Logs are retained and occasionally shared with third-party observability tools.

Jiffy IntelApr 27

Credential ExfilLow

Claude Project knowledge file contains hardcoded API tokens

Project uploader accidentally includes a knowledge file (often a README or internal doc) that has API tokens embedded. Any team member running the project can view the file, and the tokens enter model context on every turn.

Jiffy IntelApr 27

MCP server stores AWS credentials in world-readable file

Summary

Severity & confidence

High

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

MITRE ATT&CK T1555 — Credentials from Password Stores

OWASP LLM-02: Sensitive Information Disclosure (2026)

Scan for patterns like this