privacy-masking
Mask sensitive visual data in video evidence such as faces, license plates, phone numbers, and doorplates. Use when Codex has an evidence image URI, sensitive_regions, or privacy_masking config and ne
SKILL.mdskills/custom/video_surveillance/privacy-masking/SKILL.md
GitHubPrivacy Masking
Execution Priority
Prioritize calling this skill's scripts/run.py entrypoint first. Only write custom code after the script result is unsuitable or the script cannot cover the requested task.
Input Resolution
If an evidence image URI is missing but the user provided an event or video analysis request, do not write custom masking code. First call evidence-snapshot/scripts/run.py to create snapshot evidence, then call this skill on the resulting evidence URI when masking is required.
Atomic CLI
Run this skill directly with its own script. The script does not call other skill scripts and does not depend on shared src, tools, or registry modules.
python privacy-masking/scripts/run.py --image-uri <image.jpg> --sensitive-regions-json <regions.json> --config <config.json> --output <masked.json>
Parameters: --image-uri, --sensitive-regions-json, --method, --disabled, --config, --output.
Workflow
- Read evidence URI and configured mask types.
- Locate or accept sensitive regions.
- Apply configured blur, mosaic, or solid mask.
- Return masked URI, mask status, regions, and method.
Available Implementation
This skill is implemented as an atomic standalone script in its own scripts/run.py. The script contains the executable logic for this skill and must not import shared src, tools, or registry modules.
Inputs
uriorimage_uri- Optional
sensitive_regions: list of bboxes or region dicts - Optional
output_keyfor memory storage mode
Outputs
Returns uri, privacy_masked, masked_regions, and method.
Failure Modes
MISSING_URIIMAGE_READ_FAILED
Constraints
Do not delete original evidence needed for traceability.