Install
$ agentstack add skill-redhatproductsecurity-prodsec-skills-secdevai-fix ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Security Fix Application
Applies security fixes identified by a prior code review. Always shows a diff preview and requires explicit user approval before modifying any file.
When to Use This Skill
- Applying fixes for findings from a prior
secdevai-reviewor equivalent
security review
- Applying a filtered subset of fixes (e.g., only critical severity findings)
- Previewing proposed code changes before deciding whether to apply them
Workflow
Step 1: Verify Prerequisites
Confirm that a prior security review has been run and findings are available. If no prior review exists, inform the user and suggest running a security review first.
Step 2: Apply Severity Filter (optional)
If the user specifies a severity level (critical, high, medium, low), limit fixes to findings at that level or above. If no filter is specified, present all available fixes.
Step 3: Present Fixes
For each fix, show:
- Finding: Description and location (file and line number)
- Severity: The severity of the finding being fixed
- OWASP / CWE reference: Category and ID
- Before: The vulnerable code
- After: The fixed code
- Security impact: What the fix prevents
Example:
## Fix #1 (Critical)
**Finding**: SQL Injection in `app.py:42`
**OWASP Category**: [A03: Injection](https://owasp.org/Top10/A03_2021-Injection/) ([CWE-89](https://cwe.mitre.org/data/definitions/89.html))
**Before**:
query = f"SELECT * FROM users WHERE id = {user_id}"
**After**:
cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))
**Security impact**: Eliminates SQL injection by using a parameterized query.
The database driver handles escaping, preventing attacker-controlled input from
modifying query structure.
Step 4: Require Explicit Approval
Before applying any changes:
- Show all proposed diffs
- Ask the user to confirm which fixes to apply
- Never modify code without explicit approval
- Never apply fixes in bulk without showing each change first
Step 5: Apply Approved Fixes
After the user approves:
- Apply the approved code changes exactly as shown in the preview
- Report which fixes were applied and which were skipped
- If a fix cannot be applied cleanly (e.g., the file has changed), report the
conflict and leave the file unchanged
Important Rules
- Always preview before modifying: Show the exact diff before touching any
file.
- Never apply without approval: Require explicit confirmation, even when the
user says "apply all".
- Respect scope: Only fix findings from the current review session unless the
user explicitly provides findings from elsewhere.
- Report outcomes: After applying, list what changed and what was skipped,
with reasons.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: RedHatProductSecurity
- Source: RedHatProductSecurity/prodsec-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.