The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external articles to detect rhetorical techniques, creating an attack surface for indirect prompt injection. However, the risk is mitigated by using a local rule-based script rather than direct prompt interpolation.\n
Ingestion points: scripts/analyze.py reads article content from external files provided by the user.\n
Boundary markers: The skill does not employ specific delimiters to separate processed data from internal instructions.\n
Capability inventory: The skill has the capability to write JSON and Markdown reports to the local filesystem.\n
Sanitization: Input data is cleaned and extracted using specific regular expressions for loaded language and source attribution.\n- [SAFE]: The skill demonstrates safe coding practices. No obfuscation, persistence mechanisms, or unauthorized privilege escalations were found. The implementation relies exclusively on the Python standard library and performs no network operations.

media-analyzer