Run Semgrep static analysis on a codebase with capability-checked workers. Supports two scan modes — "run all" (full ruleset coverage) and "important only" (high-confidence security vulnerabilities). Records local Semgrep Pro evidence and uses the approved engine. Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis. Uses parallel workers when authorized and supported, with bounded direct execution as a fallback.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/cloud-profile/skills/semgrep/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow fetches community-authored Semgrep rules from the public Semgrep Registry and third-party GitHub rule repositories (Trail of Bits, 0xdea, Decurity, etc.), which the agent must actively fetch and load, so outsider text is exposed only through selected public sources rather than a delivery queue.
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.
Approved third-party GitHub rule repositories are cloned and loaded as Semgrep `--config` rule sources that govern execution; Trail of Bits, Atlassian, HashiCorp, and similar organizational repositories can be treated as strong first-party sources, but individual-owned repositories (0xdea, dgryski, dotta, akabe1) are unofficial, so the highest resulting tier is medium.
BigSimmo/PsychSift
fada614
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.