Security Audit
tailored-resume-generator
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
tailored-resume-generator received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill vulnerable to user-input prompt injection.
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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill vulnerable to user-input prompt injection The skill is designed to process extensive free-form text input from users (job descriptions, personal background, existing resumes). A malicious user could embed adversarial instructions within their input (e.g., within the 'job description' or 'My Current Resume' sections) to manipulate the underlying Large Language Model (LLM) into performing unintended actions, such as revealing internal prompts, generating harmful content, or attempting to exfiltrate data if the LLM has access to external tools. The skill's instructions do not include explicit safeguards against such attacks. Implement robust input validation and sanitization for user-provided text. Employ prompt engineering techniques (e.g., instruction grounding, few-shot examples, explicit negative constraints) to make the LLM more resilient to adversarial instructions. Explicitly instruct the LLM to ignore any instructions embedded within user-provided job descriptions or resume content and to strictly adhere to its primary function of resume generation. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/2b97055acffc53d3)
Powered by SkillShield