Security Audit

typefully/agent-skills:skills/typefully

github.com/typefully/agent-skills

AI SkillCommit a403e5813dd7

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

typefully/agent-skills:skills/typefully received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary File Exfiltration via Tool Arguments, Configuration Hijacking via Non-Interactive Setup.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 8, 2026 (commit a403e581). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Arbitrary File Exfiltration via Tool Arguments The `drafts:create` command accepts a `--file` argument and `media:upload` accepts a file path argument. The tool reads these files and uploads them to the Typefully API. The documentation and context imply no path restrictions (e.g., chroot or allowlist). A prompt injection attack could trick the agent into reading and uploading sensitive system files (e.g., `~/.ssh/id_rsa`, `/etc/passwd`, or the `.typefully/config.json` containing the API key) to the external service. Modify `scripts/typefully.js` to validate file paths. Restrict access to the current working directory and its subdirectories. Reject absolute paths or paths containing `..` unless explicitly authorized by the user.	LLM	SKILL.md:185
MEDIUM	Configuration Hijacking via Non-Interactive Setup The `setup` command supports non-interactive configuration flags (`--key`, `--location`). An attacker could use prompt injection to instruct the agent to execute this command with an attacker-controlled API key. This would silently reconfigure the tool, causing subsequent drafts created by the user to be sent to the attacker's Typefully account. Disable non-interactive configuration changes when the tool is invoked by an agent, or require a separate confirmation step that the agent cannot automate.	LLM	SKILL.md:222

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f19509888e126221.svg)](https://skillshield.io/report/f19509888e126221)