owasp-top10-2025-cwe-reviewer
Review real software repositories for likely security issues using the local OWASP Top 10:2025 category set, official OWASP-mapped CWE lists, and canonical MITRE CWE records. Use when auditing source code, configuration, IaC, pipelines, dependencies, auth flows, crypto, logging, or error handling, and when the goal is evidence-based findings mapped to both CWE and OWASP 2025 with confidence levels and coverage gaps.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Security
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 0.90). The skill explicitly requires citing "concrete repository evidence" with file:line excerpts and calls out "embedded secrets" as a detection target but gives no guidance to redact or avoid quoting secret values, which effectively encourages outputting secrets verbatim when present.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The builder workflow (scripts/build_knowledge_pack.py) fetches live OWASP pages (e.g. https://owasp.org/Top10/2025/) and the MITRE CWE XML feed (https://cwe.mitre.org/data/xml/cwec_latest.xml.zip) when refreshing the local knowledge pack, and that fetched content is normalized into the knowledge pack which directly controls the skill's prompts/ mappings at runtime.
- Commit
0d7f002
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.