The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several local Python scripts to perform core functions, passing user-supplied input as command-line arguments.
Evidence found in SKILL.md:
python scripts/dfs_client.py serp --keyword "<target news topic>"
python scripts/dfs_client.py onpage --url "<article-url>"
python scripts/dfs_client.py ranked --target "<publication-domain>" --limit 100
python scripts/schema_gen.py newsarticle --field headline="..." ...
python scripts/report_publish.py <report>.md
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external publication domains and article URLs using the webfetch tool and dfs_client.py. This data is subsequently processed to generate SEO audits, JSON-LD schema, and client reports.
Ingestion points: External article URLs and publication domains are fetched and analyzed.
Boundary markers: None identified; external content is interpolated directly into the auditing process.
Capability inventory: The skill has the ability to execute subprocesses (via python scripts/...) and write report files to the local filesystem (NEWS-SEO-<domain>-<date>.md).
Sanitization: There is no explicit evidence of sanitization or escaping of the content retrieved from external URLs before it is processed by the scripts or the agent.

news-seo